Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3610 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.4139. Min Act: -0.0000

Data Index: 277748 (The Pile)

Max Activating Token Index: 221

Text #1

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.4157. Min Act: -0.0000

Data Index: 513796 (The Pile)

Max Activating Token Index: 586

Text #2

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1965507 (The Pile)

Max Activating Token Index: 976

Text #3

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1238347 (The Pile)

Max Activating Token Index: 855

Text #4

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3666. Min Act: -0.0000

Data Index: 1129993 (The Pile)

Max Activating Token Index: 453

Text #5

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3712. Min Act: -0.0000

Data Index: 96845 (The Pile)

Max Activating Token Index: 136

Text #6

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1267761 (The Pile)

Max Activating Token Index: 418

Text #7

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1698874 (The Pile)

Max Activating Token Index: 518

Text #8

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1259453 (The Pile)

Max Activating Token Index: 845

Text #9

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3504. Min Act: -0.0000

Data Index: 665951 (The Pile)

Max Activating Token Index: 837

Text #10

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3715. Min Act: 0.0000

Data Index: 401448 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3460. Min Act: -0.0000

Data Index: 258852 (The Pile)

Max Activating Token Index: 777

Text #12

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3604. Min Act: -0.0000

Data Index: 1888813 (The Pile)

Max Activating Token Index: 315

Text #13

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1488782 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3433. Min Act: -0.0000

Data Index: 629412 (The Pile)

Max Activating Token Index: 647

Text #15

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3381. Min Act: -0.0000

Data Index: 151297 (The Pile)

Max Activating Token Index: 77

Text #16

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1683415 (The Pile)

Max Activating Token Index: 754

Text #17

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1498132 (The Pile)

Max Activating Token Index: 634

Text #18

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3247. Min Act: 0.0000

Data Index: 1377579 (The Pile)

Max Activating Token Index: 141

Text #19

Max Range: 0.4157. Min Range: -0.4157

Max Act: 0.3228. Min Act: -0.0000

Data Index: 1864466 (The Pile)

Max Activating Token Index: 497