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

Dataset: The Pile

Neuron 2912 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.9429. Min Act: -0.0000

Data Index: 1939463 (The Pile)

Max Activating Token Index: 544

Text #1

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1433553 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8178. Min Act: -0.0000

Data Index: 393905 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1952152 (The Pile)

Max Activating Token Index: 763

Text #4

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7868. Min Act: -0.0000

Data Index: 124136 (The Pile)

Max Activating Token Index: 418

Text #5

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7191. Min Act: -0.0000

Data Index: 855978 (The Pile)

Max Activating Token Index: 764

Text #6

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7023. Min Act: -0.0000

Data Index: 481404 (The Pile)

Max Activating Token Index: 406

Text #7

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7683. Min Act: -0.0000

Data Index: 491196 (The Pile)

Max Activating Token Index: 946

Text #8

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1024190 (The Pile)

Max Activating Token Index: 892

Text #9

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1335327 (The Pile)

Max Activating Token Index: 765

Text #10

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.5688. Min Act: -0.0000

Data Index: 636126 (The Pile)

Max Activating Token Index: 776

Text #11

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1274126 (The Pile)

Max Activating Token Index: 756

Text #12

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.5963. Min Act: -0.0000

Data Index: 457423 (The Pile)

Max Activating Token Index: 894

Text #13

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.3883. Min Act: -0.0000

Data Index: 577051 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.4459. Min Act: -0.0000

Data Index: 976936 (The Pile)

Max Activating Token Index: 485

Text #15

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.3707. Min Act: -0.0000

Data Index: 5515 (The Pile)

Max Activating Token Index: 303

Text #16

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.4074. Min Act: -0.0000

Data Index: 890283 (The Pile)

Max Activating Token Index: 432

Text #17

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.4076. Min Act: -0.0000

Data Index: 1465122 (The Pile)

Max Activating Token Index: 115

Text #18

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.2523. Min Act: -0.0000

Data Index: 908598 (The Pile)

Max Activating Token Index: 641

Text #19

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1173972 (The Pile)

Max Activating Token Index: 537