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

Dataset: Open Web Text

Neuron 6 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: 3.3027. Min Range: -3.3027

Max Act: 3.3027. Min Act: -0.1700

Data Index: 7368003 (Open Web Text)

Max Activating Token Index: 577

Text #1

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2399. Min Act: -0.1700

Data Index: 8791168 (Open Web Text)

Max Activating Token Index: 546

Text #2

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2695. Min Act: -0.1700

Data Index: 5404263 (Open Web Text)

Max Activating Token Index: 724

Text #3

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2322. Min Act: -0.1700

Data Index: 7855721 (Open Web Text)

Max Activating Token Index: 66

Text #4

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2120. Min Act: -0.1700

Data Index: 6799851 (Open Web Text)

Max Activating Token Index: 98

Text #5

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2069. Min Act: -0.1700

Data Index: 1482832 (Open Web Text)

Max Activating Token Index: 940

Text #6

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.1973. Min Act: -0.1700

Data Index: 7818480 (Open Web Text)

Max Activating Token Index: 1011

Text #7

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.2038. Min Act: -0.1700

Data Index: 5798948 (Open Web Text)

Max Activating Token Index: 728

Text #8

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.1923. Min Act: -0.1700

Data Index: 3973450 (Open Web Text)

Max Activating Token Index: 525

Text #9

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.1813. Min Act: -0.1700

Data Index: 3504252 (Open Web Text)

Max Activating Token Index: 804

Text #10

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.1662. Min Act: -0.1700

Data Index: 4707054 (Open Web Text)

Max Activating Token Index: 447

Text #11

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.1613. Min Act: -0.1700

Data Index: 5811574 (Open Web Text)

Max Activating Token Index: 124

Text #12

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.1485. Min Act: -0.1700

Data Index: 2365390 (Open Web Text)

Max Activating Token Index: 722

Text #13

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.1340. Min Act: -0.1700

Data Index: 3181895 (Open Web Text)

Max Activating Token Index: 84

Text #14

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.1265. Min Act: -0.1700

Data Index: 2688095 (Open Web Text)

Max Activating Token Index: 547

Text #15

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.1218. Min Act: -0.1700

Data Index: 676875 (Open Web Text)

Max Activating Token Index: 733

Text #16

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.1222. Min Act: -0.1700

Data Index: 3023114 (Open Web Text)

Max Activating Token Index: 931

Text #17

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.1244. Min Act: -0.1700

Data Index: 2849656 (Open Web Text)

Max Activating Token Index: 272

Text #18

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.1203. Min Act: -0.1700

Data Index: 7105822 (Open Web Text)

Max Activating Token Index: 134

Text #19

Max Range: 3.3027. Min Range: -3.3027

Max Act: 3.1185. Min Act: -0.1700

Data Index: 8000915 (Open Web Text)

Max Activating Token Index: 63