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

Dataset: Open Web Text

Neuron 1147 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: 1.9034. Min Range: -1.9034

Max Act: 1.9034. Min Act: -0.1698

Data Index: 3266461 (Open Web Text)

Max Activating Token Index: 32

Text #1

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8959. Min Act: -0.1700

Data Index: 3852798 (Open Web Text)

Max Activating Token Index: 46

Text #2

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8724. Min Act: -0.1700

Data Index: 2499120 (Open Web Text)

Max Activating Token Index: 106

Text #3

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8683. Min Act: -0.1700

Data Index: 4590295 (Open Web Text)

Max Activating Token Index: 120

Text #4

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8355. Min Act: -0.1700

Data Index: 1545303 (Open Web Text)

Max Activating Token Index: 168

Text #5

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8308. Min Act: -0.1700

Data Index: 731353 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8382. Min Act: -0.1699

Data Index: 3852799 (Open Web Text)

Max Activating Token Index: 78

Text #7

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8152. Min Act: -0.1700

Data Index: 5513072 (Open Web Text)

Max Activating Token Index: 39

Text #8

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8260. Min Act: -0.1700

Data Index: 7392731 (Open Web Text)

Max Activating Token Index: 154

Text #9

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8184. Min Act: -0.1700

Data Index: 2199957 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8189. Min Act: -0.1700

Data Index: 2871134 (Open Web Text)

Max Activating Token Index: 406

Text #11

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8268. Min Act: -0.1700

Data Index: 1279466 (Open Web Text)

Max Activating Token Index: 416

Text #12

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8160. Min Act: -0.1700

Data Index: 5170861 (Open Web Text)

Max Activating Token Index: 84

Text #13

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8055. Min Act: -0.1700

Data Index: 6484577 (Open Web Text)

Max Activating Token Index: 17

Text #14

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8096. Min Act: -0.1700

Data Index: 6860961 (Open Web Text)

Max Activating Token Index: 158

Text #15

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8028. Min Act: -0.1700

Data Index: 6966291 (Open Web Text)

Max Activating Token Index: 75

Text #16

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8083. Min Act: -0.1700

Data Index: 3143324 (Open Web Text)

Max Activating Token Index: 182

Text #17

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8076. Min Act: -0.1700

Data Index: 7364453 (Open Web Text)

Max Activating Token Index: 18

Text #18

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.7967. Min Act: -0.1700

Data Index: 6103684 (Open Web Text)

Max Activating Token Index: 49

Text #19

Max Range: 1.9034. Min Range: -1.9034

Max Act: 1.8013. Min Act: -0.1700

Data Index: 3684350 (Open Web Text)

Max Activating Token Index: 285