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

Dataset: Open Web Text

Neuron 745 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: 1.9222. Min Range: -1.9222

Max Act: 1.9222. Min Act: -0.1700

Data Index: 3184339 (Open Web Text)

Max Activating Token Index: 44

Text #1

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.9000. Min Act: -0.1700

Data Index: 3504967 (Open Web Text)

Max Activating Token Index: 46

Text #2

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8581. Min Act: -0.1700

Data Index: 2468902 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8543. Min Act: -0.1700

Data Index: 4285483 (Open Web Text)

Max Activating Token Index: 348

Text #4

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8484. Min Act: -0.1700

Data Index: 174324 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8277. Min Act: -0.1700

Data Index: 4749914 (Open Web Text)

Max Activating Token Index: 909

Text #6

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8153. Min Act: -0.1700

Data Index: 6179835 (Open Web Text)

Max Activating Token Index: 60

Text #7

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8373. Min Act: -0.1700

Data Index: 4249238 (Open Web Text)

Max Activating Token Index: 375

Text #8

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8148. Min Act: -0.1700

Data Index: 5269893 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8257. Min Act: -0.1700

Data Index: 7022568 (Open Web Text)

Max Activating Token Index: 255

Text #10

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8106. Min Act: -0.1700

Data Index: 586882 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8030. Min Act: -0.1700

Data Index: 7925761 (Open Web Text)

Max Activating Token Index: 14

Text #12

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8081. Min Act: -0.1700

Data Index: 5334474 (Open Web Text)

Max Activating Token Index: 14

Text #13

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8230. Min Act: -0.1700

Data Index: 1743984 (Open Web Text)

Max Activating Token Index: 575

Text #14

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8003. Min Act: -0.1700

Data Index: 4827630 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.7843. Min Act: -0.1700

Data Index: 2157472 (Open Web Text)

Max Activating Token Index: 581

Text #16

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8086. Min Act: -0.1700

Data Index: 4083548 (Open Web Text)

Max Activating Token Index: 575

Text #17

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8077. Min Act: -0.1700

Data Index: 434790 (Open Web Text)

Max Activating Token Index: 923

Text #18

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.7936. Min Act: -0.1700

Data Index: 5953634 (Open Web Text)

Max Activating Token Index: 270

Text #19

Max Range: 1.9222. Min Range: -1.9222

Max Act: 1.8086. Min Act: -0.1700

Data Index: 4083545 (Open Web Text)

Max Activating Token Index: 575