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

Dataset: The Pile

Neuron 3048 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: 0.9493. Min Range: -0.9493

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1106546 (The Pile)

Max Activating Token Index: 627

Text #1

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1618999 (The Pile)

Max Activating Token Index: 623

Text #2

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.8632. Min Act: -0.0000

Data Index: 3455 (The Pile)

Max Activating Token Index: 1000

Text #3

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.8058. Min Act: 0.0000

Data Index: 1995123 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.7519. Min Act: -0.0000

Data Index: 210048 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.7282. Min Act: 0.0000

Data Index: 1906084 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.7911. Min Act: -0.0000

Data Index: 454466 (The Pile)

Max Activating Token Index: 613

Text #7

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1932922 (The Pile)

Max Activating Token Index: 292

Text #8

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.5722. Min Act: -0.0000

Data Index: 163450 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1262845 (The Pile)

Max Activating Token Index: 871

Text #10

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6084. Min Act: -0.0000

Data Index: 657506 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1610043 (The Pile)

Max Activating Token Index: 777

Text #12

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6877. Min Act: -0.0000

Data Index: 982905 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6292. Min Act: 0.0000

Data Index: 1824470 (The Pile)

Max Activating Token Index: 110

Text #14

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6862. Min Act: 0.0000

Data Index: 1873393 (The Pile)

Max Activating Token Index: 980

Text #15

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6058. Min Act: -0.0000

Data Index: 807375 (The Pile)

Max Activating Token Index: 155

Text #16

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6805. Min Act: -0.0000

Data Index: 1889822 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6463. Min Act: -0.0000

Data Index: 593722 (The Pile)

Max Activating Token Index: 375

Text #18

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6226. Min Act: 0.0000

Data Index: 533300 (The Pile)

Max Activating Token Index: 473

Text #19

Max Range: 0.9493. Min Range: -0.9493

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1776129 (The Pile)

Max Activating Token Index: 193