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

Dataset: Open Web Text

Neuron 636 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: 4.2742. Min Range: -4.2742

Max Act: 4.2742. Min Act: -0.1700

Data Index: 1332099 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 4.2742. Min Range: -4.2742

Max Act: 4.2298. Min Act: -0.1700

Data Index: 5992698 (Open Web Text)

Max Activating Token Index: 91

Text #2

Max Range: 4.2742. Min Range: -4.2742

Max Act: 4.1953. Min Act: -0.1700

Data Index: 7750585 (Open Web Text)

Max Activating Token Index: 45

Text #3

Max Range: 4.2742. Min Range: -4.2742

Max Act: 4.1495. Min Act: -0.1700

Data Index: 1005611 (Open Web Text)

Max Activating Token Index: 52

Text #4

Max Range: 4.2742. Min Range: -4.2742

Max Act: 4.0925. Min Act: -0.1700

Data Index: 8319895 (Open Web Text)

Max Activating Token Index: 720

Text #5

Max Range: 4.2742. Min Range: -4.2742

Max Act: 4.0843. Min Act: -0.1700

Data Index: 3827168 (Open Web Text)

Max Activating Token Index: 893

Text #6

Max Range: 4.2742. Min Range: -4.2742

Max Act: 4.0408. Min Act: -0.1696

Data Index: 4496485 (Open Web Text)

Max Activating Token Index: 943

Text #7

Max Range: 4.2742. Min Range: -4.2742

Max Act: 4.0087. Min Act: -0.1700

Data Index: 5059006 (Open Web Text)

Max Activating Token Index: 911

Text #8

Max Range: 4.2742. Min Range: -4.2742

Max Act: 3.9843. Min Act: -0.1700

Data Index: 2127952 (Open Web Text)

Max Activating Token Index: 188

Text #9

Max Range: 4.2742. Min Range: -4.2742

Max Act: 4.0197. Min Act: -0.1700

Data Index: 1836518 (Open Web Text)

Max Activating Token Index: 1012

Text #10

Max Range: 4.2742. Min Range: -4.2742

Max Act: 3.9583. Min Act: -0.1700

Data Index: 6477173 (Open Web Text)

Max Activating Token Index: 379

Text #11

Max Range: 4.2742. Min Range: -4.2742

Max Act: 3.9579. Min Act: -0.1700

Data Index: 6801274 (Open Web Text)

Max Activating Token Index: 53

Text #12

Max Range: 4.2742. Min Range: -4.2742

Max Act: 3.9395. Min Act: -0.1700

Data Index: 2198988 (Open Web Text)

Max Activating Token Index: 304

Text #13

Max Range: 4.2742. Min Range: -4.2742

Max Act: 3.9707. Min Act: -0.1700

Data Index: 3741037 (Open Web Text)

Max Activating Token Index: 253

Text #14

Max Range: 4.2742. Min Range: -4.2742

Max Act: 3.9494. Min Act: -0.1700

Data Index: 6923423 (Open Web Text)

Max Activating Token Index: 814

Text #15

Max Range: 4.2742. Min Range: -4.2742

Max Act: 3.9616. Min Act: -0.1700

Data Index: 959081 (Open Web Text)

Max Activating Token Index: 132

Text #16

Max Range: 4.2742. Min Range: -4.2742

Max Act: 3.9432. Min Act: -0.1700

Data Index: 3913404 (Open Web Text)

Max Activating Token Index: 563

Text #17

Max Range: 4.2742. Min Range: -4.2742

Max Act: 3.9254. Min Act: -0.1700

Data Index: 2615488 (Open Web Text)

Max Activating Token Index: 664

Text #18

Max Range: 4.2742. Min Range: -4.2742

Max Act: 3.9331. Min Act: -0.1700

Data Index: 6858796 (Open Web Text)

Max Activating Token Index: 463

Text #19

Max Range: 4.2742. Min Range: -4.2742

Max Act: 3.9186. Min Act: -0.1700

Data Index: 2009922 (Open Web Text)

Max Activating Token Index: 18