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

Dataset: Open Web Text

Neuron 2249 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: 2.3805. Min Range: -2.3805

Max Act: 2.3805. Min Act: -0.1699

Data Index: 1423564 (Open Web Text)

Max Activating Token Index: 356

Text #1

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.3171. Min Act: -0.1700

Data Index: 1223234 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2820. Min Act: -0.1700

Data Index: 3491126 (Open Web Text)

Max Activating Token Index: 257

Text #3

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2802. Min Act: -0.1700

Data Index: 1423565 (Open Web Text)

Max Activating Token Index: 43

Text #4

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2856. Min Act: -0.1700

Data Index: 4602155 (Open Web Text)

Max Activating Token Index: 162

Text #5

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2631. Min Act: -0.1700

Data Index: 7598063 (Open Web Text)

Max Activating Token Index: 588

Text #6

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2607. Min Act: -0.1700

Data Index: 1731760 (Open Web Text)

Max Activating Token Index: 1003

Text #7

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2125. Min Act: -0.1700

Data Index: 6598303 (Open Web Text)

Max Activating Token Index: 654

Text #8

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2331. Min Act: -0.1700

Data Index: 5607025 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2236. Min Act: -0.1700

Data Index: 36414 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2292. Min Act: -0.1700

Data Index: 534971 (Open Web Text)

Max Activating Token Index: 251

Text #11

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2357. Min Act: -0.1700

Data Index: 5550466 (Open Web Text)

Max Activating Token Index: 443

Text #12

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2309. Min Act: -0.1700

Data Index: 8087182 (Open Web Text)

Max Activating Token Index: 71

Text #13

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2123. Min Act: -0.1700

Data Index: 5989058 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.1993. Min Act: -0.1700

Data Index: 4459702 (Open Web Text)

Max Activating Token Index: 135

Text #15

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2107. Min Act: -0.1700

Data Index: 4159523 (Open Web Text)

Max Activating Token Index: 410

Text #16

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.1927. Min Act: -0.1700

Data Index: 327104 (Open Web Text)

Max Activating Token Index: 632

Text #17

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2025. Min Act: -0.1700

Data Index: 220777 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2037. Min Act: -0.1700

Data Index: 5331325 (Open Web Text)

Max Activating Token Index: 8

Text #19

Max Range: 2.3805. Min Range: -2.3805

Max Act: 2.2055. Min Act: -0.1700

Data Index: 6739179 (Open Web Text)

Max Activating Token Index: 98