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

Dataset: The Pile

Neuron 3086 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: 3.1987. Min Range: -3.1987

Max Act: 3.1987. Min Act: -0.0000

Data Index: 203787 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 3.1987. Min Range: -3.1987

Max Act: 3.0918. Min Act: -0.0000

Data Index: 1134836 (The Pile)

Max Activating Token Index: 467

Text #2

Max Range: 3.1987. Min Range: -3.1987

Max Act: 2.6771. Min Act: -0.0000

Data Index: 698138 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 3.1987. Min Range: -3.1987

Max Act: 2.7474. Min Act: -0.0000

Data Index: 504787 (The Pile)

Max Activating Token Index: 680

Text #4

Max Range: 3.1987. Min Range: -3.1987

Max Act: 2.1346. Min Act: -0.0000

Data Index: 540362 (The Pile)

Max Activating Token Index: 377

Text #5

Max Range: 3.1987. Min Range: -3.1987

Max Act: 2.2498. Min Act: -0.0000

Data Index: 1789314 (The Pile)

Max Activating Token Index: 422

Text #6

Max Range: 3.1987. Min Range: -3.1987

Max Act: 2.1364. Min Act: -0.0000

Data Index: 1903302 (The Pile)

Max Activating Token Index: 677

Text #7

Max Range: 3.1987. Min Range: -3.1987

Max Act: 2.2592. Min Act: -0.0000

Data Index: 1732495 (The Pile)

Max Activating Token Index: 918

Text #8

Max Range: 3.1987. Min Range: -3.1987

Max Act: 2.2414. Min Act: -0.0000

Data Index: 138347 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 3.1987. Min Range: -3.1987

Max Act: 2.1028. Min Act: -0.0000

Data Index: 1739446 (The Pile)

Max Activating Token Index: 890

Text #10

Max Range: 3.1987. Min Range: -3.1987

Max Act: 2.0834. Min Act: -0.0000

Data Index: 480065 (The Pile)

Max Activating Token Index: 182

Text #11

Max Range: 3.1987. Min Range: -3.1987

Max Act: 1.9655. Min Act: -0.0000

Data Index: 1269625 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 3.1987. Min Range: -3.1987

Max Act: 1.9989. Min Act: -0.0000

Data Index: 130195 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 3.1987. Min Range: -3.1987

Max Act: 2.0395. Min Act: -0.0000

Data Index: 335507 (The Pile)

Max Activating Token Index: 265

Text #14

Max Range: 3.1987. Min Range: -3.1987

Max Act: 2.1216. Min Act: -0.0000

Data Index: 1851328 (The Pile)

Max Activating Token Index: 402

Text #15

Max Range: 3.1987. Min Range: -3.1987

Max Act: 2.1247. Min Act: -0.0000

Data Index: 1979982 (The Pile)

Max Activating Token Index: 408

Text #16

Max Range: 3.1987. Min Range: -3.1987

Max Act: 1.9808. Min Act: -0.0000

Data Index: 461511 (The Pile)

Max Activating Token Index: 906

Text #17

Max Range: 3.1987. Min Range: -3.1987

Max Act: 1.8575. Min Act: -0.0000

Data Index: 366998 (The Pile)

Max Activating Token Index: 410

Text #18

Max Range: 3.1987. Min Range: -3.1987

Max Act: 1.8614. Min Act: -0.0000

Data Index: 835884 (The Pile)

Max Activating Token Index: 621

Text #19

Max Range: 3.1987. Min Range: -3.1987

Max Act: 2.0286. Min Act: -0.0000

Data Index: 942735 (The Pile)

Max Activating Token Index: 256