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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4415 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.8925. Min Act: -0.0000

Data Index: 79809 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.6495. Min Act: -0.0000

Data Index: 249539 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.4669. Min Act: -0.0000

Data Index: 1250457 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.3681. Min Act: -0.0000

Data Index: 866355 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.3731. Min Act: -0.0000

Data Index: 674090 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.4233. Min Act: -0.0000

Data Index: 667826 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.2586. Min Act: -0.0000

Data Index: 712851 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.3248. Min Act: -0.0000

Data Index: 1225383 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.2475. Min Act: -0.0000

Data Index: 1034454 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.3062. Min Act: -0.0000

Data Index: 151252 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.2412. Min Act: -0.0000

Data Index: 386002 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.3542. Min Act: -0.0000

Data Index: 480541 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.2853. Min Act: -0.0000

Data Index: 208537 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.2615. Min Act: -0.0000

Data Index: 1146101 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.2972. Min Act: -0.0000

Data Index: 850518 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.1479. Min Act: -0.0000

Data Index: 174695 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.0999. Min Act: -0.0000

Data Index: 417748 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.0989. Min Act: -0.0000

Data Index: 456470 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.0804. Min Act: -0.0000

Data Index: 1279111 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 1.8925. Min Range: -1.8925

Max Act: 1.2213. Min Act: -0.0000

Data Index: 396050 (C4 (Web Text))

Max Activating Token Index: 205