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

Dataset: The Pile

Neuron 4834 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: 1.0195. Min Range: -1.0195

Max Act: 1.0195. Min Act: -0.0000

Data Index: 1692168 (The Pile)

Max Activating Token Index: 695

Text #1

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.9655. Min Act: -0.0000

Data Index: 597151 (The Pile)

Max Activating Token Index: 110

Text #2

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8585. Min Act: -0.0000

Data Index: 1622132 (The Pile)

Max Activating Token Index: 1014

Text #3

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1819416 (The Pile)

Max Activating Token Index: 55

Text #4

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8339. Min Act: -0.0000

Data Index: 170760 (The Pile)

Max Activating Token Index: 472

Text #5

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8302. Min Act: -0.0000

Data Index: 1302698 (The Pile)

Max Activating Token Index: 447

Text #6

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8237. Min Act: -0.0000

Data Index: 31689 (The Pile)

Max Activating Token Index: 56

Text #7

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8567. Min Act: -0.0000

Data Index: 366723 (The Pile)

Max Activating Token Index: 300

Text #8

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7725. Min Act: -0.0000

Data Index: 1445894 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7249. Min Act: -0.0000

Data Index: 631351 (The Pile)

Max Activating Token Index: 879

Text #10

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1308826 (The Pile)

Max Activating Token Index: 389

Text #11

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7958. Min Act: -0.0000

Data Index: 501899 (The Pile)

Max Activating Token Index: 868

Text #12

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7712. Min Act: -0.0000

Data Index: 226747 (The Pile)

Max Activating Token Index: 160

Text #13

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1055247 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1571478 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7446. Min Act: -0.0000

Data Index: 1549338 (The Pile)

Max Activating Token Index: 931

Text #16

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1252888 (The Pile)

Max Activating Token Index: 164

Text #17

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7682. Min Act: -0.0000

Data Index: 1055332 (The Pile)

Max Activating Token Index: 290

Text #18

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1358317 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 1.0195. Min Range: -1.0195

Max Act: 0.7624. Min Act: -0.0000

Data Index: 1250369 (The Pile)

Max Activating Token Index: 494