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

Dataset: The Pile

Neuron 1275 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.4316. Min Act: -0.0000

Data Index: 659609 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.4014. Min Act: -0.0000

Data Index: 1024581 (The Pile)

Max Activating Token Index: 477

Text #2

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.4012. Min Act: 0.0001

Data Index: 264126 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1056561 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3622. Min Act: -0.0000

Data Index: 380739 (The Pile)

Max Activating Token Index: 960

Text #5

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1930641 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1556192 (The Pile)

Max Activating Token Index: 319

Text #7

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3508. Min Act: -0.0000

Data Index: 41390 (The Pile)

Max Activating Token Index: 205

Text #8

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3333. Min Act: -0.0000

Data Index: 721347 (The Pile)

Max Activating Token Index: 565

Text #9

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3444. Min Act: -0.0000

Data Index: 200338 (The Pile)

Max Activating Token Index: 736

Text #10

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.2978. Min Act: -0.0000

Data Index: 1797237 (The Pile)

Max Activating Token Index: 546

Text #11

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3156. Min Act: -0.0000

Data Index: 1584455 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1796311 (The Pile)

Max Activating Token Index: 576

Text #13

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.3004. Min Act: -0.0000

Data Index: 457353 (The Pile)

Max Activating Token Index: 60

Text #14

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.2833. Min Act: 0.0000

Data Index: 243762 (The Pile)

Max Activating Token Index: 374

Text #15

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1834792 (The Pile)

Max Activating Token Index: 431

Text #16

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1391082 (The Pile)

Max Activating Token Index: 135

Text #17

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1677764 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1487884 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 0.4316. Min Range: -0.4316

Max Act: 0.2955. Min Act: 0.0000

Data Index: 1651569 (The Pile)

Max Activating Token Index: 624