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

Dataset: Open Web Text

Neuron 86 in Layer 6

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: 4.8736. Min Range: -4.8736

Max Act: 4.8736. Min Act: -0.1700

Data Index: 5261841 (Open Web Text)

Max Activating Token Index: 62

Text #1

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.8709. Min Act: -0.1700

Data Index: 7514173 (Open Web Text)

Max Activating Token Index: 211

Text #2

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.8179. Min Act: -0.1700

Data Index: 7303300 (Open Web Text)

Max Activating Token Index: 187

Text #3

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.8020. Min Act: -0.1700

Data Index: 2536504 (Open Web Text)

Max Activating Token Index: 599

Text #4

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.6213. Min Act: -0.1700

Data Index: 7581889 (Open Web Text)

Max Activating Token Index: 495

Text #5

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.6429. Min Act: -0.1700

Data Index: 6535208 (Open Web Text)

Max Activating Token Index: 96

Text #6

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.6191. Min Act: -0.1700

Data Index: 8375681 (Open Web Text)

Max Activating Token Index: 776

Text #7

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.5869. Min Act: -0.1700

Data Index: 2496927 (Open Web Text)

Max Activating Token Index: 431

Text #8

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.5863. Min Act: -0.1700

Data Index: 3400691 (Open Web Text)

Max Activating Token Index: 73

Text #9

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.5745. Min Act: -0.1700

Data Index: 308328 (Open Web Text)

Max Activating Token Index: 79

Text #10

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.5582. Min Act: -0.1700

Data Index: 539582 (Open Web Text)

Max Activating Token Index: 279

Text #11

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.5583. Min Act: -0.1700

Data Index: 5585491 (Open Web Text)

Max Activating Token Index: 498

Text #12

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.5655. Min Act: -0.1700

Data Index: 2984939 (Open Web Text)

Max Activating Token Index: 90

Text #13

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.5256. Min Act: -0.1700

Data Index: 8708675 (Open Web Text)

Max Activating Token Index: 263

Text #14

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.4983. Min Act: -0.1700

Data Index: 1821804 (Open Web Text)

Max Activating Token Index: 463

Text #15

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.5338. Min Act: -0.1700

Data Index: 586842 (Open Web Text)

Max Activating Token Index: 381

Text #16

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.5130. Min Act: -0.1700

Data Index: 6688516 (Open Web Text)

Max Activating Token Index: 154

Text #17

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.4831. Min Act: -0.1700

Data Index: 7605808 (Open Web Text)

Max Activating Token Index: 924

Text #18

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.5025. Min Act: -0.1700

Data Index: 1872365 (Open Web Text)

Max Activating Token Index: 896

Text #19

Max Range: 4.8736. Min Range: -4.8736

Max Act: 4.4854. Min Act: -0.1700

Data Index: 4010767 (Open Web Text)

Max Activating Token Index: 268