< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 70 in Layer 25

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 12.1840. Min Range: -12.1840

Max Act: 12.1840. Min Act: -0.1700

Data Index: 4351819 (Open Web Text)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 12.1840. Min Range: -12.1840

Max Act: 12.1840. Min Act: -0.1699

Data Index: 8233530 (Open Web Text)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.9965. Min Act: -0.1700

Data Index: 4205500 (Open Web Text)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.9340. Min Act: -0.1700

Data Index: 2760441 (Open Web Text)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.9965. Min Act: -0.1700

Data Index: 995169 (Open Web Text)

Max Activating Token Index: 707

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.9340. Min Act: -0.1700

Data Index: 3738813 (Open Web Text)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.8715. Min Act: -0.1700

Data Index: 315892 (Open Web Text)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.8715. Min Act: -0.1700

Data Index: 1947980 (Open Web Text)

Max Activating Token Index: 300

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.7465. Min Act: -0.1700

Data Index: 4430431 (Open Web Text)

Max Activating Token Index: 304

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.7465. Min Act: -0.1700

Data Index: 4897683 (Open Web Text)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.7465. Min Act: -0.1700

Data Index: 4725179 (Open Web Text)

Max Activating Token Index: 281

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.7465. Min Act: -0.1700

Data Index: 785530 (Open Web Text)

Max Activating Token Index: 806

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.6215. Min Act: -0.1700

Data Index: 419348 (Open Web Text)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.6840. Min Act: -0.1700

Data Index: 2366668 (Open Web Text)

Max Activating Token Index: 743

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.6215. Min Act: -0.1700

Data Index: 6668876 (Open Web Text)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.6215. Min Act: -0.1700

Data Index: 6522658 (Open Web Text)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.6215. Min Act: -0.1700

Data Index: 6234114 (Open Web Text)

Max Activating Token Index: 749

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.5590. Min Act: -0.1700

Data Index: 1204910 (Open Web Text)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.5590. Min Act: -0.1700

Data Index: 2408753 (Open Web Text)

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 12.1840. Min Range: -12.1840

Max Act: 11.6215. Min Act: -0.1700

Data Index: 3375326 (Open Web Text)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #19