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

Dataset: Open Web Text

Neuron 1068 in Layer 5

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: 5.2266. Min Range: -5.2266

Max Act: 5.2194. Min Act: -0.1700

Data Index: 4153331 (Open Web Text)

Max Activating Token Index: 305

Text #1

Max Range: 5.2266. Min Range: -5.2266

Max Act: 5.2266. Min Act: -0.1700

Data Index: 4889039 (Open Web Text)

Max Activating Token Index: 773

Text #2

Max Range: 5.2266. Min Range: -5.2266

Max Act: 5.1301. Min Act: -0.1700

Data Index: 5992416 (Open Web Text)

Max Activating Token Index: 314

Text #3

Max Range: 5.2266. Min Range: -5.2266

Max Act: 5.0978. Min Act: -0.1700

Data Index: 409298 (Open Web Text)

Max Activating Token Index: 214

Text #4

Max Range: 5.2266. Min Range: -5.2266

Max Act: 5.1115. Min Act: -0.1700

Data Index: 8660984 (Open Web Text)

Max Activating Token Index: 68

Text #5

Max Range: 5.2266. Min Range: -5.2266

Max Act: 5.0387. Min Act: -0.1700

Data Index: 4453376 (Open Web Text)

Max Activating Token Index: 561

Text #6

Max Range: 5.2266. Min Range: -5.2266

Max Act: 5.0241. Min Act: -0.1700

Data Index: 4306563 (Open Web Text)

Max Activating Token Index: 687

Text #7

Max Range: 5.2266. Min Range: -5.2266

Max Act: 5.0154. Min Act: -0.1700

Data Index: 7780783 (Open Web Text)

Max Activating Token Index: 13

Text #8

Max Range: 5.2266. Min Range: -5.2266

Max Act: 4.9873. Min Act: -0.1700

Data Index: 877117 (Open Web Text)

Max Activating Token Index: 214

Text #9

Max Range: 5.2266. Min Range: -5.2266

Max Act: 4.9751. Min Act: -0.1700

Data Index: 2756821 (Open Web Text)

Max Activating Token Index: 947

Text #10

Max Range: 5.2266. Min Range: -5.2266

Max Act: 4.9825. Min Act: -0.1700

Data Index: 7867551 (Open Web Text)

Max Activating Token Index: 696

Text #11

Max Range: 5.2266. Min Range: -5.2266

Max Act: 4.9748. Min Act: -0.1700

Data Index: 5333102 (Open Web Text)

Max Activating Token Index: 752

Text #12

Max Range: 5.2266. Min Range: -5.2266

Max Act: 4.9636. Min Act: -0.1700

Data Index: 2935822 (Open Web Text)

Max Activating Token Index: 144

Text #13

Max Range: 5.2266. Min Range: -5.2266

Max Act: 4.9573. Min Act: -0.1700

Data Index: 8027635 (Open Web Text)

Max Activating Token Index: 24

Text #14

Max Range: 5.2266. Min Range: -5.2266

Max Act: 4.9607. Min Act: -0.1700

Data Index: 7121063 (Open Web Text)

Max Activating Token Index: 21

Text #15

Max Range: 5.2266. Min Range: -5.2266

Max Act: 4.9461. Min Act: -0.1700

Data Index: 6058626 (Open Web Text)

Max Activating Token Index: 154

Text #16

Max Range: 5.2266. Min Range: -5.2266

Max Act: 4.9274. Min Act: -0.1700

Data Index: 8691479 (Open Web Text)

Max Activating Token Index: 89

Text #17

Max Range: 5.2266. Min Range: -5.2266

Max Act: 4.9368. Min Act: -0.1700

Data Index: 5417517 (Open Web Text)

Max Activating Token Index: 940

Text #18

Max Range: 5.2266. Min Range: -5.2266

Max Act: 4.9007. Min Act: -0.1700

Data Index: 111480 (Open Web Text)

Max Activating Token Index: 761

Text #19

Max Range: 5.2266. Min Range: -5.2266

Max Act: 4.8919. Min Act: -0.1700

Data Index: 5310124 (Open Web Text)

Max Activating Token Index: 72