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

Dataset: Open Web Text

Neuron 74 in Layer 6

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: 5.1971. Min Range: -5.1971

Max Act: 5.1971. Min Act: -0.1700

Data Index: 3061987 (Open Web Text)

Max Activating Token Index: 953

Text #1

Max Range: 5.1971. Min Range: -5.1971

Max Act: 5.0941. Min Act: -0.1700

Data Index: 6143154 (Open Web Text)

Max Activating Token Index: 971

Text #2

Max Range: 5.1971. Min Range: -5.1971

Max Act: 5.0548. Min Act: -0.1700

Data Index: 3497470 (Open Web Text)

Max Activating Token Index: 412

Text #3

Max Range: 5.1971. Min Range: -5.1971

Max Act: 5.0419. Min Act: -0.1700

Data Index: 1342173 (Open Web Text)

Max Activating Token Index: 970

Text #4

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.9313. Min Act: -0.1700

Data Index: 6855632 (Open Web Text)

Max Activating Token Index: 769

Text #5

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.9376. Min Act: -0.1700

Data Index: 7900186 (Open Web Text)

Max Activating Token Index: 562

Text #6

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.9716. Min Act: -0.1700

Data Index: 110321 (Open Web Text)

Max Activating Token Index: 1004

Text #7

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.9214. Min Act: -0.1700

Data Index: 6653602 (Open Web Text)

Max Activating Token Index: 707

Text #8

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.9033. Min Act: -0.1700

Data Index: 6036904 (Open Web Text)

Max Activating Token Index: 184

Text #9

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.9004. Min Act: -0.1700

Data Index: 8496814 (Open Web Text)

Max Activating Token Index: 271

Text #10

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.9151. Min Act: -0.1700

Data Index: 7327648 (Open Web Text)

Max Activating Token Index: 998

Text #11

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.8848. Min Act: -0.1700

Data Index: 4227465 (Open Web Text)

Max Activating Token Index: 774

Text #12

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.9168. Min Act: -0.1700

Data Index: 6151831 (Open Web Text)

Max Activating Token Index: 372

Text #13

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.8484. Min Act: -0.1700

Data Index: 6083483 (Open Web Text)

Max Activating Token Index: 935

Text #14

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.8765. Min Act: -0.1700

Data Index: 8766622 (Open Web Text)

Max Activating Token Index: 341

Text #15

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.8562. Min Act: -0.1700

Data Index: 6342477 (Open Web Text)

Max Activating Token Index: 357

Text #16

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.8363. Min Act: -0.1700

Data Index: 51730 (Open Web Text)

Max Activating Token Index: 910

Text #17

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.8271. Min Act: -0.1700

Data Index: 1185158 (Open Web Text)

Max Activating Token Index: 461

Text #18

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.8458. Min Act: -0.1700

Data Index: 6046619 (Open Web Text)

Max Activating Token Index: 959

Text #19

Max Range: 5.1971. Min Range: -5.1971

Max Act: 4.8220. Min Act: -0.1700

Data Index: 5282183 (Open Web Text)

Max Activating Token Index: 998