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

Dataset: The Pile

Neuron 626 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: 0.3567. Min Range: -0.3567

Max Act: 0.3567. Min Act: -0.0000

Data Index: 390312 (The Pile)

Max Activating Token Index: 909

Text #1

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1463344 (The Pile)

Max Activating Token Index: 27

Text #2

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3297. Min Act: -0.0000

Data Index: 414478 (The Pile)

Max Activating Token Index: 109

Text #3

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2940. Min Act: -0.0000

Data Index: 1628545 (The Pile)

Max Activating Token Index: 762

Text #4

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1273183 (The Pile)

Max Activating Token Index: 20

Text #5

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1357495 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2953. Min Act: -0.0000

Data Index: 776943 (The Pile)

Max Activating Token Index: 883

Text #7

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2674. Min Act: -0.0000

Data Index: 710263 (The Pile)

Max Activating Token Index: 570

Text #8

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2819. Min Act: -0.0000

Data Index: 705803 (The Pile)

Max Activating Token Index: 459

Text #9

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2652. Min Act: -0.0000

Data Index: 761094 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2652. Min Act: -0.0000

Data Index: 827994 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1552063 (The Pile)

Max Activating Token Index: 351

Text #12

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2624. Min Act: -0.0000

Data Index: 369165 (The Pile)

Max Activating Token Index: 588

Text #13

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2762. Min Act: -0.0000

Data Index: 886584 (The Pile)

Max Activating Token Index: 749

Text #14

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1495271 (The Pile)

Max Activating Token Index: 584

Text #15

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1788107 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2637. Min Act: -0.0000

Data Index: 1571401 (The Pile)

Max Activating Token Index: 122

Text #17

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1733720 (The Pile)

Max Activating Token Index: 471

Text #18

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1646393 (The Pile)

Max Activating Token Index: 560

Text #19

Max Range: 0.3567. Min Range: -0.3567

Max Act: 0.2485. Min Act: -0.0000

Data Index: 363238 (The Pile)

Max Activating Token Index: 529