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

Dataset: Open Web Text

Neuron 903 in Layer 4

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: 4.8394. Min Range: -4.8394

Max Act: 4.8394. Min Act: -0.1700

Data Index: 7260563 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.7863. Min Act: -0.1700

Data Index: 123132 (Open Web Text)

Max Activating Token Index: 286

Text #2

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6876. Min Act: -0.1700

Data Index: 8561509 (Open Web Text)

Max Activating Token Index: 187

Text #3

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6917. Min Act: -0.1700

Data Index: 7757718 (Open Web Text)

Max Activating Token Index: 1015

Text #4

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6534. Min Act: -0.1700

Data Index: 3691058 (Open Web Text)

Max Activating Token Index: 388

Text #5

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6358. Min Act: -0.1700

Data Index: 7797397 (Open Web Text)

Max Activating Token Index: 644

Text #6

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6270. Min Act: -0.1700

Data Index: 1957682 (Open Web Text)

Max Activating Token Index: 913

Text #7

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6324. Min Act: -0.1700

Data Index: 5545139 (Open Web Text)

Max Activating Token Index: 294

Text #8

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.5474. Min Act: -0.1700

Data Index: 6045803 (Open Web Text)

Max Activating Token Index: 564

Text #9

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.5912. Min Act: -0.1700

Data Index: 7541226 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6602. Min Act: -0.1700

Data Index: 4342659 (Open Web Text)

Max Activating Token Index: 385

Text #11

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6143. Min Act: -0.1700

Data Index: 3425768 (Open Web Text)

Max Activating Token Index: 49

Text #12

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.6404. Min Act: -0.1700

Data Index: 1890115 (Open Web Text)

Max Activating Token Index: 124

Text #13

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.5997. Min Act: -0.1700

Data Index: 3592619 (Open Web Text)

Max Activating Token Index: 113

Text #14

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.5572. Min Act: -0.1700

Data Index: 7960738 (Open Web Text)

Max Activating Token Index: 62

Text #15

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.5486. Min Act: -0.1700

Data Index: 1509346 (Open Web Text)

Max Activating Token Index: 355

Text #16

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.5754. Min Act: -0.1700

Data Index: 438752 (Open Web Text)

Max Activating Token Index: 10

Text #17

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.5843. Min Act: -0.1700

Data Index: 4544276 (Open Web Text)

Max Activating Token Index: 879

Text #18

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.5733. Min Act: -0.1700

Data Index: 5689349 (Open Web Text)

Max Activating Token Index: 799

Text #19

Max Range: 4.8394. Min Range: -4.8394

Max Act: 4.5790. Min Act: -0.1700

Data Index: 3298434 (Open Web Text)

Max Activating Token Index: 104