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

Dataset: Open Web Text

Neuron 1800 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: 4.7710. Min Range: -4.7710

Max Act: 4.7710. Min Act: -0.1700

Data Index: 2204490 (Open Web Text)

Max Activating Token Index: 251

Text #1

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.6451. Min Act: -0.1700

Data Index: 7316580 (Open Web Text)

Max Activating Token Index: 478

Text #2

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.5740. Min Act: -0.1700

Data Index: 7610049 (Open Web Text)

Max Activating Token Index: 38

Text #3

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.5291. Min Act: -0.1700

Data Index: 7330649 (Open Web Text)

Max Activating Token Index: 237

Text #4

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.5222. Min Act: -0.1700

Data Index: 891942 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.5324. Min Act: -0.1700

Data Index: 8515946 (Open Web Text)

Max Activating Token Index: 455

Text #6

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.4561. Min Act: -0.1700

Data Index: 6793417 (Open Web Text)

Max Activating Token Index: 402

Text #7

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.4267. Min Act: -0.1700

Data Index: 2555678 (Open Web Text)

Max Activating Token Index: 919

Text #8

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.4504. Min Act: -0.1700

Data Index: 4438967 (Open Web Text)

Max Activating Token Index: 243

Text #9

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.5015. Min Act: -0.1700

Data Index: 7606670 (Open Web Text)

Max Activating Token Index: 283

Text #10

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.4231. Min Act: -0.1700

Data Index: 5772604 (Open Web Text)

Max Activating Token Index: 239

Text #11

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.4702. Min Act: -0.1700

Data Index: 6678610 (Open Web Text)

Max Activating Token Index: 827

Text #12

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.4393. Min Act: -0.1700

Data Index: 3103747 (Open Web Text)

Max Activating Token Index: 582

Text #13

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.4255. Min Act: -0.1700

Data Index: 2459973 (Open Web Text)

Max Activating Token Index: 762

Text #14

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.4587. Min Act: -0.1700

Data Index: 3073479 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.4129. Min Act: -0.1700

Data Index: 1180485 (Open Web Text)

Max Activating Token Index: 965

Text #16

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.4353. Min Act: -0.1700

Data Index: 1125540 (Open Web Text)

Max Activating Token Index: 962

Text #17

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.4503. Min Act: -0.1700

Data Index: 3345478 (Open Web Text)

Max Activating Token Index: 893

Text #18

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.3729. Min Act: -0.1700

Data Index: 3126874 (Open Web Text)

Max Activating Token Index: 764

Text #19

Max Range: 4.7710. Min Range: -4.7710

Max Act: 4.4001. Min Act: -0.1700

Data Index: 5221921 (Open Web Text)

Max Activating Token Index: 945