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

Dataset: The Pile

Neuron 2029 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7767. Min Act: -0.0000

Data Index: 1476334 (The Pile)

Max Activating Token Index: 359

Text #1

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7751. Min Act: -0.0000

Data Index: 391328 (The Pile)

Max Activating Token Index: 208

Text #2

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6924. Min Act: 0.0000

Data Index: 169661 (The Pile)

Max Activating Token Index: 149

Text #3

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7475. Min Act: -0.0000

Data Index: 119489 (The Pile)

Max Activating Token Index: 483

Text #4

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1478693 (The Pile)

Max Activating Token Index: 145

Text #5

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1778744 (The Pile)

Max Activating Token Index: 795

Text #6

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6635. Min Act: -0.0000

Data Index: 987295 (The Pile)

Max Activating Token Index: 644

Text #7

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1930934 (The Pile)

Max Activating Token Index: 506

Text #8

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6407. Min Act: -0.0000

Data Index: 924669 (The Pile)

Max Activating Token Index: 909

Text #9

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6323. Min Act: -0.0000

Data Index: 74898 (The Pile)

Max Activating Token Index: 902

Text #10

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1938149 (The Pile)

Max Activating Token Index: 638

Text #11

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6450. Min Act: -0.0000

Data Index: 924112 (The Pile)

Max Activating Token Index: 397

Text #12

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6585. Min Act: -0.0000

Data Index: 1907464 (The Pile)

Max Activating Token Index: 310

Text #13

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1556316 (The Pile)

Max Activating Token Index: 307

Text #14

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6010. Min Act: -0.0000

Data Index: 839207 (The Pile)

Max Activating Token Index: 405

Text #15

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.6025. Min Act: -0.0000

Data Index: 875351 (The Pile)

Max Activating Token Index: 176

Text #16

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5734. Min Act: -0.0000

Data Index: 693463 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1852806 (The Pile)

Max Activating Token Index: 131

Text #18

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5901. Min Act: -0.0000

Data Index: 824729 (The Pile)

Max Activating Token Index: 536

Text #19

Max Range: 0.7767. Min Range: -0.7767

Max Act: 0.5953. Min Act: -0.0000

Data Index: 165707 (The Pile)

Max Activating Token Index: 139