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

Dataset: The Pile

Neuron 3208 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6915. Min Act: -0.0000

Data Index: 151275 (The Pile)

Max Activating Token Index: 315

Text #1

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6185. Min Act: -0.0000

Data Index: 946372 (The Pile)

Max Activating Token Index: 251

Text #2

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1811532 (The Pile)

Max Activating Token Index: 369

Text #3

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5468. Min Act: -0.0000

Data Index: 832300 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5447. Min Act: -0.0000

Data Index: 850126 (The Pile)

Max Activating Token Index: 34

Text #5

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5877. Min Act: -0.0000

Data Index: 849110 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6193. Min Act: -0.0000

Data Index: 993342 (The Pile)

Max Activating Token Index: 889

Text #7

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1542541 (The Pile)

Max Activating Token Index: 421

Text #8

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5166. Min Act: -0.0000

Data Index: 354882 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1757818 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1329812 (The Pile)

Max Activating Token Index: 803

Text #11

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5419. Min Act: -0.0000

Data Index: 60800 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4936. Min Act: -0.0000

Data Index: 291779 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4843. Min Act: -0.0000

Data Index: 907365 (The Pile)

Max Activating Token Index: 84

Text #14

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5471. Min Act: -0.0000

Data Index: 835628 (The Pile)

Max Activating Token Index: 206

Text #15

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4455. Min Act: -0.0000

Data Index: 19078 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1260556 (The Pile)

Max Activating Token Index: 619

Text #17

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1506877 (The Pile)

Max Activating Token Index: 274

Text #18

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1766674 (The Pile)

Max Activating Token Index: 426

Text #19

Max Range: 0.6915. Min Range: -0.6915

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1992430 (The Pile)

Max Activating Token Index: 429