Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4146 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1867353 (The Pile)

Max Activating Token Index: 671

Text #1

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3967. Min Act: -0.0000

Data Index: 450661 (The Pile)

Max Activating Token Index: 751

Text #2

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3366. Min Act: -0.0000

Data Index: 333751 (The Pile)

Max Activating Token Index: 153

Text #3

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3744. Min Act: -0.0000

Data Index: 1422910 (The Pile)

Max Activating Token Index: 53

Text #4

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1351541 (The Pile)

Max Activating Token Index: 514

Text #5

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1040268 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3234. Min Act: -0.0000

Data Index: 1347340 (The Pile)

Max Activating Token Index: 675

Text #7

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1348313 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1375338 (The Pile)

Max Activating Token Index: 873

Text #9

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3311. Min Act: -0.0000

Data Index: 1773659 (The Pile)

Max Activating Token Index: 1012

Text #10

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3291. Min Act: -0.0000

Data Index: 290581 (The Pile)

Max Activating Token Index: 732

Text #11

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3211. Min Act: -0.0000

Data Index: 1321009 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3149. Min Act: -0.0000

Data Index: 1238417 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3226. Min Act: -0.0000

Data Index: 349426 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2796. Min Act: -0.0000

Data Index: 1902369 (The Pile)

Max Activating Token Index: 662

Text #15

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1745725 (The Pile)

Max Activating Token Index: 363

Text #16

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.3009. Min Act: -0.0000

Data Index: 965519 (The Pile)

Max Activating Token Index: 353

Text #17

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2733. Min Act: -0.0000

Data Index: 976203 (The Pile)

Max Activating Token Index: 606

Text #18

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2624. Min Act: -0.0000

Data Index: 369761 (The Pile)

Max Activating Token Index: 17

Text #19

Max Range: 0.5037. Min Range: -0.5037

Max Act: 0.2905. Min Act: -0.0000

Data Index: 15293 (The Pile)

Max Activating Token Index: 569