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

Dataset: Open Web Text

Neuron 1708 in Layer 0

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: 1.6738. Min Range: -1.6738

Max Act: 1.6738. Min Act: -0.1227

Data Index: 324854 (Open Web Text)

Max Activating Token Index: 85

Text #1

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5777. Min Act: -0.1227

Data Index: 2436301 (Open Web Text)

Max Activating Token Index: 925

Text #2

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5804. Min Act: -0.1630

Data Index: 6193226 (Open Web Text)

Max Activating Token Index: 312

Text #3

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5755. Min Act: -0.1227

Data Index: 302128 (Open Web Text)

Max Activating Token Index: 904

Text #4

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5678. Min Act: -0.1227

Data Index: 7127952 (Open Web Text)

Max Activating Token Index: 305

Text #5

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5493. Min Act: -0.1227

Data Index: 5563663 (Open Web Text)

Max Activating Token Index: 277

Text #6

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5376. Min Act: -0.1227

Data Index: 302136 (Open Web Text)

Max Activating Token Index: 252

Text #7

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5404. Min Act: -0.1227

Data Index: 4193808 (Open Web Text)

Max Activating Token Index: 974

Text #8

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5416. Min Act: -0.1227

Data Index: 302132 (Open Web Text)

Max Activating Token Index: 473

Text #9

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5337. Min Act: -0.1227

Data Index: 3506433 (Open Web Text)

Max Activating Token Index: 979

Text #10

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5421. Min Act: -0.1227

Data Index: 1852217 (Open Web Text)

Max Activating Token Index: 895

Text #11

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5193. Min Act: -0.1227

Data Index: 5852986 (Open Web Text)

Max Activating Token Index: 950

Text #12

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5224. Min Act: -0.1227

Data Index: 302135 (Open Web Text)

Max Activating Token Index: 1021

Text #13

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5228. Min Act: -0.1327

Data Index: 7908283 (Open Web Text)

Max Activating Token Index: 966

Text #14

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5228. Min Act: -0.1227

Data Index: 2267771 (Open Web Text)

Max Activating Token Index: 451

Text #15

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5221. Min Act: -0.1227

Data Index: 6782082 (Open Web Text)

Max Activating Token Index: 385

Text #16

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5273. Min Act: -0.1227

Data Index: 5530216 (Open Web Text)

Max Activating Token Index: 1008

Text #17

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5181. Min Act: -0.1227

Data Index: 4955102 (Open Web Text)

Max Activating Token Index: 970

Text #18

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5240. Min Act: -0.1324

Data Index: 2322994 (Open Web Text)

Max Activating Token Index: 851

Text #19

Max Range: 1.6738. Min Range: -1.6738

Max Act: 1.5266. Min Act: -0.1227

Data Index: 1051288 (Open Web Text)

Max Activating Token Index: 1023