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

Dataset: The Pile

Neuron 923 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1663 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.4352. Min Act: -0.0000

Data Index: 1986917 (The Pile)

Max Activating Token Index: 347

Text #2

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1333367 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3767. Min Act: -0.0000

Data Index: 1231083 (The Pile)

Max Activating Token Index: 282

Text #4

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1130335 (The Pile)

Max Activating Token Index: 833

Text #5

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3285. Min Act: -0.0000

Data Index: 1417911 (The Pile)

Max Activating Token Index: 115

Text #6

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1062166 (The Pile)

Max Activating Token Index: 914

Text #7

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3570. Min Act: -0.0000

Data Index: 985744 (The Pile)

Max Activating Token Index: 188

Text #8

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3463. Min Act: -0.0000

Data Index: 308162 (The Pile)

Max Activating Token Index: 545

Text #9

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1216280 (The Pile)

Max Activating Token Index: 118

Text #10

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3614. Min Act: -0.0000

Data Index: 635150 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3636. Min Act: -0.0000

Data Index: 1990223 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3505. Min Act: -0.0000

Data Index: 858144 (The Pile)

Max Activating Token Index: 341

Text #13

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3309. Min Act: -0.0000

Data Index: 580587 (The Pile)

Max Activating Token Index: 796

Text #14

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3405. Min Act: -0.0000

Data Index: 379876 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3485. Min Act: -0.0000

Data Index: 422778 (The Pile)

Max Activating Token Index: 943

Text #16

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1699771 (The Pile)

Max Activating Token Index: 52

Text #17

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3567. Min Act: -0.0000

Data Index: 1541337 (The Pile)

Max Activating Token Index: 166

Text #18

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1319119 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 0.5045. Min Range: -0.5045

Max Act: 0.3354. Min Act: -0.0000

Data Index: 217886 (The Pile)

Max Activating Token Index: 187