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

Dataset: Open Web Text

Neuron 2168 in Layer 2

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: 4.0875. Min Range: -4.0875

Max Act: 4.0875. Min Act: -0.1700

Data Index: 5447883 (Open Web Text)

Max Activating Token Index: 33

Text #1

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.8583. Min Act: -0.1700

Data Index: 3959065 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.7234. Min Act: -0.1700

Data Index: 4071824 (Open Web Text)

Max Activating Token Index: 37

Text #3

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.6369. Min Act: -0.1700

Data Index: 3583315 (Open Web Text)

Max Activating Token Index: 198

Text #4

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.6073. Min Act: -0.1700

Data Index: 6529353 (Open Web Text)

Max Activating Token Index: 134

Text #5

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.6393. Min Act: -0.1700

Data Index: 6628089 (Open Web Text)

Max Activating Token Index: 935

Text #6

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.6269. Min Act: -0.1700

Data Index: 5985301 (Open Web Text)

Max Activating Token Index: 424

Text #7

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.6045. Min Act: -0.1700

Data Index: 4136597 (Open Web Text)

Max Activating Token Index: 764

Text #8

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.5986. Min Act: -0.1700

Data Index: 4273026 (Open Web Text)

Max Activating Token Index: 936

Text #9

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.5610. Min Act: -0.1700

Data Index: 7809846 (Open Web Text)

Max Activating Token Index: 369

Text #10

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.5608. Min Act: -0.1700

Data Index: 4132441 (Open Web Text)

Max Activating Token Index: 80

Text #11

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.5502. Min Act: -0.1700

Data Index: 2390796 (Open Web Text)

Max Activating Token Index: 947

Text #12

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.5527. Min Act: -0.1700

Data Index: 1809357 (Open Web Text)

Max Activating Token Index: 107

Text #13

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.5157. Min Act: -0.1700

Data Index: 327269 (Open Web Text)

Max Activating Token Index: 930

Text #14

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.5306. Min Act: -0.1700

Data Index: 7310125 (Open Web Text)

Max Activating Token Index: 934

Text #15

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.5368. Min Act: -0.1700

Data Index: 4449074 (Open Web Text)

Max Activating Token Index: 449

Text #16

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.5058. Min Act: -0.1700

Data Index: 8355247 (Open Web Text)

Max Activating Token Index: 88

Text #17

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.5103. Min Act: -0.1700

Data Index: 3466176 (Open Web Text)

Max Activating Token Index: 342

Text #18

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.5170. Min Act: -0.1700

Data Index: 3855117 (Open Web Text)

Max Activating Token Index: 64

Text #19

Max Range: 4.0875. Min Range: -4.0875

Max Act: 3.5152. Min Act: -0.1700

Data Index: 7730534 (Open Web Text)

Max Activating Token Index: 107