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

Dataset: The Pile

Neuron 1261 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: 0.6138. Min Range: -0.6138

Max Act: 0.6138. Min Act: -0.0000

Data Index: 560977 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1143834 (The Pile)

Max Activating Token Index: 212

Text #2

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4673. Min Act: -0.0000

Data Index: 775017 (The Pile)

Max Activating Token Index: 398

Text #3

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4559. Min Act: -0.0000

Data Index: 13902 (The Pile)

Max Activating Token Index: 312

Text #4

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1560252 (The Pile)

Max Activating Token Index: 319

Text #5

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3535. Min Act: -0.0000

Data Index: 1071320 (The Pile)

Max Activating Token Index: 81

Text #6

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1942814 (The Pile)

Max Activating Token Index: 318

Text #7

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1661053 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3251. Min Act: -0.0000

Data Index: 977887 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3361. Min Act: -0.0000

Data Index: 788937 (The Pile)

Max Activating Token Index: 545

Text #10

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3098. Min Act: -0.0000

Data Index: 1801477 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1553598 (The Pile)

Max Activating Token Index: 779

Text #12

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.2850. Min Act: -0.0000

Data Index: 586984 (The Pile)

Max Activating Token Index: 979

Text #13

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1843871 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.2859. Min Act: -0.0000

Data Index: 543782 (The Pile)

Max Activating Token Index: 597

Text #15

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1113069 (The Pile)

Max Activating Token Index: 981

Text #16

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3728. Min Act: -0.0000

Data Index: 227154 (The Pile)

Max Activating Token Index: 489

Text #17

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1399016 (The Pile)

Max Activating Token Index: 390

Text #18

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1806496 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 0.6138. Min Range: -0.6138

Max Act: 0.3396. Min Act: -0.0000

Data Index: 36609 (The Pile)

Max Activating Token Index: 588