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

Dataset: The Pile

Neuron 4075 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: 0.5251. Min Range: -0.5251

Max Act: 0.5251. Min Act: -0.0000

Data Index: 240685 (The Pile)

Max Activating Token Index: 545

Text #1

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4727. Min Act: -0.0000

Data Index: 598435 (The Pile)

Max Activating Token Index: 132

Text #2

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4952. Min Act: -0.0000

Data Index: 316130 (The Pile)

Max Activating Token Index: 677

Text #3

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4609. Min Act: -0.0000

Data Index: 5054 (The Pile)

Max Activating Token Index: 349

Text #4

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4155. Min Act: -0.0000

Data Index: 354127 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1891013 (The Pile)

Max Activating Token Index: 540

Text #6

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1714118 (The Pile)

Max Activating Token Index: 264

Text #7

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1611540 (The Pile)

Max Activating Token Index: 240

Text #8

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1325210 (The Pile)

Max Activating Token Index: 110

Text #9

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3543. Min Act: -0.0000

Data Index: 637622 (The Pile)

Max Activating Token Index: 652

Text #10

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1025929 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3583. Min Act: -0.0000

Data Index: 1423422 (The Pile)

Max Activating Token Index: 929

Text #12

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1700600 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3664. Min Act: -0.0000

Data Index: 984659 (The Pile)

Max Activating Token Index: 165

Text #14

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3336. Min Act: -0.0000

Data Index: 705155 (The Pile)

Max Activating Token Index: 593

Text #15

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3409. Min Act: -0.0000

Data Index: 1436650 (The Pile)

Max Activating Token Index: 642

Text #16

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3296. Min Act: -0.0000

Data Index: 671716 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3381. Min Act: -0.0000

Data Index: 1224349 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3325. Min Act: -0.0000

Data Index: 892898 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 0.5251. Min Range: -0.5251

Max Act: 0.3393. Min Act: -0.0000

Data Index: 128674 (The Pile)

Max Activating Token Index: 216