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

Dataset: Open Web Text

Neuron 931 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: 3.4859. Min Range: -3.4859

Max Act: 3.4859. Min Act: -0.1700

Data Index: 7848421 (Open Web Text)

Max Activating Token Index: 630

Text #1

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4231. Min Act: -0.1700

Data Index: 3138058 (Open Web Text)

Max Activating Token Index: 791

Text #2

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4225. Min Act: -0.1700

Data Index: 1581584 (Open Web Text)

Max Activating Token Index: 145

Text #3

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4324. Min Act: -0.1700

Data Index: 6558919 (Open Web Text)

Max Activating Token Index: 781

Text #4

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4135. Min Act: -0.1700

Data Index: 6473452 (Open Web Text)

Max Activating Token Index: 473

Text #5

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4236. Min Act: -0.1700

Data Index: 5773555 (Open Web Text)

Max Activating Token Index: 405

Text #6

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4184. Min Act: -0.1700

Data Index: 563950 (Open Web Text)

Max Activating Token Index: 115

Text #7

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3894. Min Act: -0.1700

Data Index: 6985607 (Open Web Text)

Max Activating Token Index: 1008

Text #8

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.4019. Min Act: -0.1700

Data Index: 7848415 (Open Web Text)

Max Activating Token Index: 488

Text #9

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3865. Min Act: -0.1700

Data Index: 7623115 (Open Web Text)

Max Activating Token Index: 316

Text #10

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3895. Min Act: -0.1700

Data Index: 8581486 (Open Web Text)

Max Activating Token Index: 621

Text #11

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3639. Min Act: -0.1700

Data Index: 8666492 (Open Web Text)

Max Activating Token Index: 577

Text #12

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3418. Min Act: -0.1700

Data Index: 8235211 (Open Web Text)

Max Activating Token Index: 638

Text #13

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3522. Min Act: -0.1700

Data Index: 43995 (Open Web Text)

Max Activating Token Index: 476

Text #14

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3387. Min Act: -0.1700

Data Index: 6167775 (Open Web Text)

Max Activating Token Index: 892

Text #15

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3392. Min Act: -0.1700

Data Index: 6635092 (Open Web Text)

Max Activating Token Index: 702

Text #16

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3323. Min Act: -0.1700

Data Index: 206584 (Open Web Text)

Max Activating Token Index: 824

Text #17

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3398. Min Act: -0.1700

Data Index: 3155998 (Open Web Text)

Max Activating Token Index: 98

Text #18

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3383. Min Act: -0.1700

Data Index: 2788487 (Open Web Text)

Max Activating Token Index: 956

Text #19

Max Range: 3.4859. Min Range: -3.4859

Max Act: 3.3455. Min Act: -0.1700

Data Index: 5461845 (Open Web Text)

Max Activating Token Index: 865