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

Dataset: Open Web Text

Neuron 500 in Layer 3

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: 4.8228. Min Range: -4.8228

Max Act: 4.8228. Min Act: -0.1700

Data Index: 1369402 (Open Web Text)

Max Activating Token Index: 120

Text #1

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.7072. Min Act: -0.1700

Data Index: 3546603 (Open Web Text)

Max Activating Token Index: 31

Text #2

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.6669. Min Act: -0.1700

Data Index: 5341324 (Open Web Text)

Max Activating Token Index: 355

Text #3

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.6168. Min Act: -0.1700

Data Index: 8604845 (Open Web Text)

Max Activating Token Index: 27

Text #4

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.6330. Min Act: -0.1700

Data Index: 1077113 (Open Web Text)

Max Activating Token Index: 406

Text #5

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.5859. Min Act: -0.1700

Data Index: 6831645 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.5658. Min Act: -0.1700

Data Index: 4098317 (Open Web Text)

Max Activating Token Index: 475

Text #7

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.4614. Min Act: -0.1700

Data Index: 8792241 (Open Web Text)

Max Activating Token Index: 924

Text #8

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.4784. Min Act: -0.1700

Data Index: 7904964 (Open Web Text)

Max Activating Token Index: 724

Text #9

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.5144. Min Act: -0.1700

Data Index: 5711471 (Open Web Text)

Max Activating Token Index: 1012

Text #10

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.5031. Min Act: -0.1700

Data Index: 515299 (Open Web Text)

Max Activating Token Index: 129

Text #11

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.4821. Min Act: -0.1700

Data Index: 408814 (Open Web Text)

Max Activating Token Index: 763

Text #12

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.4871. Min Act: -0.1700

Data Index: 944656 (Open Web Text)

Max Activating Token Index: 736

Text #13

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.4769. Min Act: -0.1700

Data Index: 7778791 (Open Web Text)

Max Activating Token Index: 941

Text #14

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.4918. Min Act: -0.1700

Data Index: 4299267 (Open Web Text)

Max Activating Token Index: 270

Text #15

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.4468. Min Act: -0.1700

Data Index: 5382540 (Open Web Text)

Max Activating Token Index: 751

Text #16

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.4465. Min Act: -0.1700

Data Index: 3431394 (Open Web Text)

Max Activating Token Index: 1007

Text #17

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.4428. Min Act: -0.1700

Data Index: 7378758 (Open Web Text)

Max Activating Token Index: 119

Text #18

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.4554. Min Act: -0.1700

Data Index: 6696144 (Open Web Text)

Max Activating Token Index: 299

Text #19

Max Range: 4.8228. Min Range: -4.8228

Max Act: 4.3838. Min Act: -0.1700

Data Index: 2819706 (Open Web Text)

Max Activating Token Index: 350