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

Dataset: Open Web Text

Neuron 55 in Layer 3

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: 3.9918. Min Range: -3.9918

Max Act: 3.9918. Min Act: -0.1700

Data Index: 4223368 (Open Web Text)

Max Activating Token Index: 222

Text #1

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.7302. Min Act: -0.1700

Data Index: 5324221 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.6421. Min Act: -0.1700

Data Index: 4138801 (Open Web Text)

Max Activating Token Index: 232

Text #3

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.6543. Min Act: -0.1700

Data Index: 8685444 (Open Web Text)

Max Activating Token Index: 17

Text #4

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.6393. Min Act: -0.1700

Data Index: 934949 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.6172. Min Act: -0.1700

Data Index: 3140750 (Open Web Text)

Max Activating Token Index: 30

Text #6

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.6013. Min Act: -0.1700

Data Index: 5292145 (Open Web Text)

Max Activating Token Index: 50

Text #7

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.5978. Min Act: -0.1700

Data Index: 444921 (Open Web Text)

Max Activating Token Index: 294

Text #8

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.6175. Min Act: -0.1700

Data Index: 6356218 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.5824. Min Act: -0.1700

Data Index: 4942336 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.5851. Min Act: -0.1700

Data Index: 816654 (Open Web Text)

Max Activating Token Index: 568

Text #11

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.5822. Min Act: -0.1700

Data Index: 1020609 (Open Web Text)

Max Activating Token Index: 17

Text #12

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.5455. Min Act: -0.1700

Data Index: 585724 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.5458. Min Act: -0.1700

Data Index: 2225032 (Open Web Text)

Max Activating Token Index: 398

Text #14

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.5297. Min Act: -0.1700

Data Index: 6192988 (Open Web Text)

Max Activating Token Index: 393

Text #15

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.5311. Min Act: -0.1700

Data Index: 3467284 (Open Web Text)

Max Activating Token Index: 761

Text #16

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.5461. Min Act: -0.1700

Data Index: 2863154 (Open Web Text)

Max Activating Token Index: 278

Text #17

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.5439. Min Act: -0.1700

Data Index: 7812094 (Open Web Text)

Max Activating Token Index: 18

Text #18

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.5392. Min Act: -0.1700

Data Index: 6042337 (Open Web Text)

Max Activating Token Index: 54

Text #19

Max Range: 3.9918. Min Range: -3.9918

Max Act: 3.5300. Min Act: -0.1700

Data Index: 5647630 (Open Web Text)

Max Activating Token Index: 263