Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 53 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.8787. Min Act: -0.1700

Data Index: 2987492 (Open Web Text)

Max Activating Token Index: 243

Text #1

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.7875. Min Act: -0.1700

Data Index: 5489072 (Open Web Text)

Max Activating Token Index: 135

Text #2

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.7185. Min Act: -0.1700

Data Index: 1285828 (Open Web Text)

Max Activating Token Index: 330

Text #3

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.6674. Min Act: -0.1700

Data Index: 3281738 (Open Web Text)

Max Activating Token Index: 365

Text #4

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.6723. Min Act: -0.1700

Data Index: 48490 (Open Web Text)

Max Activating Token Index: 336

Text #5

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.6919. Min Act: -0.1700

Data Index: 5336012 (Open Web Text)

Max Activating Token Index: 696

Text #6

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.6357. Min Act: -0.1700

Data Index: 6609934 (Open Web Text)

Max Activating Token Index: 269

Text #7

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.6411. Min Act: -0.1700

Data Index: 520846 (Open Web Text)

Max Activating Token Index: 543

Text #8

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.6526. Min Act: -0.1700

Data Index: 3076895 (Open Web Text)

Max Activating Token Index: 30

Text #9

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.6447. Min Act: -0.1700

Data Index: 1440718 (Open Web Text)

Max Activating Token Index: 762

Text #10

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.6337. Min Act: -0.1700

Data Index: 2493514 (Open Web Text)

Max Activating Token Index: 419

Text #11

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.6478. Min Act: -0.1700

Data Index: 7558775 (Open Web Text)

Max Activating Token Index: 537

Text #12

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.6427. Min Act: -0.1700

Data Index: 563018 (Open Web Text)

Max Activating Token Index: 674

Text #13

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.6043. Min Act: -0.1700

Data Index: 4745507 (Open Web Text)

Max Activating Token Index: 103

Text #14

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.6164. Min Act: -0.1700

Data Index: 4852966 (Open Web Text)

Max Activating Token Index: 678

Text #15

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.5838. Min Act: -0.1700

Data Index: 2181517 (Open Web Text)

Max Activating Token Index: 426

Text #16

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.6202. Min Act: -0.1700

Data Index: 4856583 (Open Web Text)

Max Activating Token Index: 310

Text #17

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.5763. Min Act: -0.1700

Data Index: 2326945 (Open Web Text)

Max Activating Token Index: 467

Text #18

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.6135. Min Act: -0.1700

Data Index: 4595126 (Open Web Text)

Max Activating Token Index: 438

Text #19

Max Range: 4.8787. Min Range: -4.8787

Max Act: 4.6080. Min Act: -0.1700

Data Index: 3727735 (Open Web Text)

Max Activating Token Index: 550