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

Dataset: Open Web Text

Neuron 1379 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: 3.5005. Min Range: -3.5005

Max Act: 3.5005. Min Act: -0.1700

Data Index: 2181064 (Open Web Text)

Max Activating Token Index: 464

Text #1

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.4552. Min Act: -0.1700

Data Index: 6279366 (Open Web Text)

Max Activating Token Index: 12

Text #2

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3608. Min Act: -0.1700

Data Index: 3990537 (Open Web Text)

Max Activating Token Index: 93

Text #3

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3538. Min Act: -0.1700

Data Index: 4865458 (Open Web Text)

Max Activating Token Index: 505

Text #4

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3494. Min Act: -0.1700

Data Index: 4776829 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3591. Min Act: -0.1700

Data Index: 2507119 (Open Web Text)

Max Activating Token Index: 427

Text #6

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3309. Min Act: -0.1700

Data Index: 6759872 (Open Web Text)

Max Activating Token Index: 933

Text #7

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3398. Min Act: -0.1700

Data Index: 2324998 (Open Web Text)

Max Activating Token Index: 890

Text #8

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3200. Min Act: -0.1700

Data Index: 6374698 (Open Web Text)

Max Activating Token Index: 1010

Text #9

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3417. Min Act: -0.1700

Data Index: 273493 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3417. Min Act: -0.1700

Data Index: 8087400 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3302. Min Act: -0.1700

Data Index: 5478659 (Open Web Text)

Max Activating Token Index: 499

Text #12

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3255. Min Act: -0.1700

Data Index: 2721076 (Open Web Text)

Max Activating Token Index: 580

Text #13

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3158. Min Act: -0.1700

Data Index: 8378439 (Open Web Text)

Max Activating Token Index: 446

Text #14

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3046. Min Act: -0.1700

Data Index: 7522548 (Open Web Text)

Max Activating Token Index: 309

Text #15

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3216. Min Act: -0.1700

Data Index: 1748823 (Open Web Text)

Max Activating Token Index: 414

Text #16

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.2914. Min Act: -0.1700

Data Index: 5985875 (Open Web Text)

Max Activating Token Index: 544

Text #17

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.2906. Min Act: -0.1700

Data Index: 4042346 (Open Web Text)

Max Activating Token Index: 922

Text #18

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.3047. Min Act: -0.1700

Data Index: 2324136 (Open Web Text)

Max Activating Token Index: 240

Text #19

Max Range: 3.5005. Min Range: -3.5005

Max Act: 3.2697. Min Act: -0.1700

Data Index: 6611782 (Open Web Text)

Max Activating Token Index: 143