< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 125 in Layer 37

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.6974. Min Act: -0.1700

Data Index: 6473431 (Open Web Text)

Max Activating Token Index: 668

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.6349. Min Act: -0.1700

Data Index: 6502127 (Open Web Text)

Max Activating Token Index: 748

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.5724. Min Act: -0.1700

Data Index: 2722391 (Open Web Text)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.4474. Min Act: -0.1700

Data Index: 5856733 (Open Web Text)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.4474. Min Act: -0.1700

Data Index: 8281356 (Open Web Text)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.3849. Min Act: -0.1700

Data Index: 4604474 (Open Web Text)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.3224. Min Act: -0.1700

Data Index: 5424068 (Open Web Text)

Max Activating Token Index: 1001

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.2599. Min Act: -0.1700

Data Index: 8024030 (Open Web Text)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.1974. Min Act: -0.1700

Data Index: 6836902 (Open Web Text)

Max Activating Token Index: 865

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.1349. Min Act: -0.1700

Data Index: 5017054 (Open Web Text)

Max Activating Token Index: 402

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.1349. Min Act: -0.1700

Data Index: 3199417 (Open Web Text)

Max Activating Token Index: 531

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.0724. Min Act: -0.1700

Data Index: 6318045 (Open Web Text)

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.0724. Min Act: -0.1700

Data Index: 4023903 (Open Web Text)

Max Activating Token Index: 265

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.0099. Min Act: -0.1700

Data Index: 2765034 (Open Web Text)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.0099. Min Act: -0.1700

Data Index: 584202 (Open Web Text)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.0099. Min Act: -0.1700

Data Index: 3689367 (Open Web Text)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 8.6974. Min Range: -8.6974

Max Act: 7.8849. Min Act: -0.1700

Data Index: 4907976 (Open Web Text)

Max Activating Token Index: 267

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 8.6974. Min Range: -8.6974

Max Act: 7.9474. Min Act: -0.1700

Data Index: 7583289 (Open Web Text)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 8.6974. Min Range: -8.6974

Max Act: 8.0099. Min Act: -0.1700

Data Index: 7203090 (Open Web Text)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 8.6974. Min Range: -8.6974

Max Act: 7.9474. Min Act: -0.1700

Data Index: 5085817 (Open Web Text)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #19