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

Dataset: The Pile

Neuron 3877 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8653. Min Range: -3.8653

Max Act: 3.7402. Min Act: -0.0000

Data Index: 664410 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 3.8653. Min Range: -3.8653

Max Act: 3.8653. Min Act: -0.0000

Data Index: 129031 (The Pile)

Max Activating Token Index: 938

Text #2

Max Range: 3.8653. Min Range: -3.8653

Max Act: 3.5083. Min Act: -0.0000

Data Index: 1267916 (The Pile)

Max Activating Token Index: 839

Text #3

Max Range: 3.8653. Min Range: -3.8653

Max Act: 3.1972. Min Act: -0.0000

Data Index: 311784 (The Pile)

Max Activating Token Index: 39

Text #4

Max Range: 3.8653. Min Range: -3.8653

Max Act: 3.5461. Min Act: -0.0000

Data Index: 1526109 (The Pile)

Max Activating Token Index: 180

Text #5

Max Range: 3.8653. Min Range: -3.8653

Max Act: 3.4466. Min Act: -0.0000

Data Index: 1428207 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 3.8653. Min Range: -3.8653

Max Act: 3.1015. Min Act: -0.0000

Data Index: 136502 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 3.8653. Min Range: -3.8653

Max Act: 3.0716. Min Act: -0.0000

Data Index: 1966907 (The Pile)

Max Activating Token Index: 70

Text #8

Max Range: 3.8653. Min Range: -3.8653

Max Act: 3.1290. Min Act: -0.0000

Data Index: 1728985 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 3.8653. Min Range: -3.8653

Max Act: 3.2364. Min Act: -0.0000

Data Index: 1737656 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 3.8653. Min Range: -3.8653

Max Act: 2.8984. Min Act: -0.0000

Data Index: 1980879 (The Pile)

Max Activating Token Index: 624

Text #11

Max Range: 3.8653. Min Range: -3.8653

Max Act: 2.9706. Min Act: -0.0000

Data Index: 480838 (The Pile)

Max Activating Token Index: 85

Text #12

Max Range: 3.8653. Min Range: -3.8653

Max Act: 2.9272. Min Act: -0.0000

Data Index: 158165 (The Pile)

Max Activating Token Index: 937

Text #13

Max Range: 3.8653. Min Range: -3.8653

Max Act: 2.8327. Min Act: -0.0000

Data Index: 820490 (The Pile)

Max Activating Token Index: 505

Text #14

Max Range: 3.8653. Min Range: -3.8653

Max Act: 2.6551. Min Act: -0.0000

Data Index: 817127 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 3.8653. Min Range: -3.8653

Max Act: 2.7669. Min Act: -0.0000

Data Index: 1814162 (The Pile)

Max Activating Token Index: 36

Text #16

Max Range: 3.8653. Min Range: -3.8653

Max Act: 2.7783. Min Act: -0.0000

Data Index: 1108307 (The Pile)

Max Activating Token Index: 929

Text #17

Max Range: 3.8653. Min Range: -3.8653

Max Act: 2.6844. Min Act: -0.0000

Data Index: 141201 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 3.8653. Min Range: -3.8653

Max Act: 2.9184. Min Act: -0.0000

Data Index: 747222 (The Pile)

Max Activating Token Index: 727

Text #19

Max Range: 3.8653. Min Range: -3.8653

Max Act: 2.7726. Min Act: -0.0000

Data Index: 230442 (The Pile)

Max Activating Token Index: 892