< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 6398 in Layer 34

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 11.6193. Min Range: -11.6193

Max Act: 11.6193. Min Act: -0.1700

Data Index: 1845133 (Open Web Text)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 11.6193. Min Range: -11.6193

Max Act: 11.3693. Min Act: -0.1700

Data Index: 5923921 (Open Web Text)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 11.6193. Min Range: -11.6193

Max Act: 11.1818. Min Act: -0.1700

Data Index: 367347 (Open Web Text)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 11.6193. Min Range: -11.6193

Max Act: 11.0568. Min Act: -0.1700

Data Index: 6074187 (Open Web Text)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.9943. Min Act: -0.1700

Data Index: 1143621 (Open Web Text)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.9318. Min Act: -0.1700

Data Index: 7974485 (Open Web Text)

Max Activating Token Index: 306

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.8068. Min Act: -0.1700

Data Index: 1833867 (Open Web Text)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.8693. Min Act: -0.1700

Data Index: 4677625 (Open Web Text)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.8693. Min Act: -0.1700

Data Index: 8478722 (Open Web Text)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.8068. Min Act: -0.1700

Data Index: 6136306 (Open Web Text)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.7443. Min Act: -0.1700

Data Index: 6535502 (Open Web Text)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.7443. Min Act: -0.1700

Data Index: 4236049 (Open Web Text)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.6818. Min Act: -0.1700

Data Index: 7052305 (Open Web Text)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.7443. Min Act: -0.1700

Data Index: 386264 (Open Web Text)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.7443. Min Act: -0.1700

Data Index: 3855221 (Open Web Text)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.6818. Min Act: -0.1700

Data Index: 2134189 (Open Web Text)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.6818. Min Act: -0.1700

Data Index: 7162319 (Open Web Text)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.6193. Min Act: -0.1700

Data Index: 4811270 (Open Web Text)

Max Activating Token Index: 914

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.6818. Min Act: -0.1700

Data Index: 2972838 (Open Web Text)

Max Activating Token Index: 665

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 11.6193. Min Range: -11.6193

Max Act: 10.6818. Min Act: -0.1700

Data Index: 6637 (Open Web Text)

Max Activating Token Index: 201

Click toggle to see full text

Truncated

Full Text #19