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

Dataset: Open Web Text

Neuron 2863 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: 3.6798. Min Range: -3.6798

Max Act: 3.6798. Min Act: -0.1700

Data Index: 4708061 (Open Web Text)

Max Activating Token Index: 366

Text #1

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.6439. Min Act: -0.1700

Data Index: 375942 (Open Web Text)

Max Activating Token Index: 825

Text #2

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.6131. Min Act: -0.1700

Data Index: 7279579 (Open Web Text)

Max Activating Token Index: 818

Text #3

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.6424. Min Act: -0.1700

Data Index: 3253662 (Open Web Text)

Max Activating Token Index: 941

Text #4

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.6097. Min Act: -0.1700

Data Index: 3043596 (Open Web Text)

Max Activating Token Index: 638

Text #5

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.6403. Min Act: -0.1700

Data Index: 1044472 (Open Web Text)

Max Activating Token Index: 585

Text #6

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.6398. Min Act: -0.1700

Data Index: 3610879 (Open Web Text)

Max Activating Token Index: 456

Text #7

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5997. Min Act: -0.1700

Data Index: 6361590 (Open Web Text)

Max Activating Token Index: 460

Text #8

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5915. Min Act: -0.1700

Data Index: 6823657 (Open Web Text)

Max Activating Token Index: 708

Text #9

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5934. Min Act: -0.1700

Data Index: 4391742 (Open Web Text)

Max Activating Token Index: 1005

Text #10

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5685. Min Act: -0.1700

Data Index: 4776722 (Open Web Text)

Max Activating Token Index: 649

Text #11

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5542. Min Act: -0.1700

Data Index: 6232673 (Open Web Text)

Max Activating Token Index: 547

Text #12

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5373. Min Act: -0.1700

Data Index: 2687551 (Open Web Text)

Max Activating Token Index: 177

Text #13

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5471. Min Act: -0.1700

Data Index: 8454192 (Open Web Text)

Max Activating Token Index: 926

Text #14

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5388. Min Act: -0.1700

Data Index: 8697987 (Open Web Text)

Max Activating Token Index: 443

Text #15

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5383. Min Act: -0.1700

Data Index: 3740342 (Open Web Text)

Max Activating Token Index: 426

Text #16

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5444. Min Act: -0.1700

Data Index: 2175114 (Open Web Text)

Max Activating Token Index: 34

Text #17

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5265. Min Act: -0.1700

Data Index: 1746829 (Open Web Text)

Max Activating Token Index: 36

Text #18

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5332. Min Act: -0.1700

Data Index: 2305928 (Open Web Text)

Max Activating Token Index: 355

Text #19

Max Range: 3.6798. Min Range: -3.6798

Max Act: 3.5147. Min Act: -0.1700

Data Index: 2789734 (Open Web Text)

Max Activating Token Index: 361