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

Dataset: Open Web Text

Neuron 3017 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: 3.1071. Min Range: -3.1071

Max Act: 3.1071. Min Act: -0.1700

Data Index: 4545152 (Open Web Text)

Max Activating Token Index: 13

Text #1

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0835. Min Act: -0.1700

Data Index: 5765663 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0639. Min Act: -0.1700

Data Index: 2629900 (Open Web Text)

Max Activating Token Index: 495

Text #3

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0576. Min Act: -0.1700

Data Index: 3924814 (Open Web Text)

Max Activating Token Index: 130

Text #4

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0538. Min Act: -0.1700

Data Index: 271076 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0459. Min Act: -0.1700

Data Index: 3599710 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0382. Min Act: -0.1700

Data Index: 2689302 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0369. Min Act: -0.1700

Data Index: 4674303 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0276. Min Act: -0.1700

Data Index: 3827329 (Open Web Text)

Max Activating Token Index: 82

Text #9

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0217. Min Act: -0.1700

Data Index: 533295 (Open Web Text)

Max Activating Token Index: 588

Text #10

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0232. Min Act: -0.1700

Data Index: 7122032 (Open Web Text)

Max Activating Token Index: 29

Text #11

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0239. Min Act: -0.1700

Data Index: 2284035 (Open Web Text)

Max Activating Token Index: 46

Text #12

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0417. Min Act: -0.1700

Data Index: 2988666 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0190. Min Act: -0.1700

Data Index: 926246 (Open Web Text)

Max Activating Token Index: 17

Text #14

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0156. Min Act: -0.1700

Data Index: 2837287 (Open Web Text)

Max Activating Token Index: 658

Text #15

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0166. Min Act: -0.1700

Data Index: 8690172 (Open Web Text)

Max Activating Token Index: 219

Text #16

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0035. Min Act: -0.1700

Data Index: 2915964 (Open Web Text)

Max Activating Token Index: 31

Text #17

Max Range: 3.1071. Min Range: -3.1071

Max Act: 2.9978. Min Act: -0.1700

Data Index: 5317050 (Open Web Text)

Max Activating Token Index: 371

Text #18

Max Range: 3.1071. Min Range: -3.1071

Max Act: 3.0042. Min Act: -0.1700

Data Index: 4456707 (Open Web Text)

Max Activating Token Index: 238

Text #19

Max Range: 3.1071. Min Range: -3.1071

Max Act: 2.9924. Min Act: -0.1700

Data Index: 6432616 (Open Web Text)

Max Activating Token Index: 106