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

Dataset: The Pile

Neuron 1131 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: 0.4961. Min Range: -0.4961

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1725784 (The Pile)

Max Activating Token Index: 73

Text #1

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1080345 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.4004. Min Act: -0.0000

Data Index: 328575 (The Pile)

Max Activating Token Index: 769

Text #3

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1914123 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3953. Min Act: -0.0000

Data Index: 604090 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3750. Min Act: -0.0000

Data Index: 1484187 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3980. Min Act: -0.0000

Data Index: 804399 (The Pile)

Max Activating Token Index: 253

Text #7

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3473. Min Act: -0.0000

Data Index: 40206 (The Pile)

Max Activating Token Index: 590

Text #8

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3815. Min Act: -0.0000

Data Index: 554743 (The Pile)

Max Activating Token Index: 527

Text #9

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1083426 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1819779 (The Pile)

Max Activating Token Index: 850

Text #11

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3868. Min Act: -0.0000

Data Index: 368994 (The Pile)

Max Activating Token Index: 95

Text #12

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3600. Min Act: -0.0000

Data Index: 743949 (The Pile)

Max Activating Token Index: 606

Text #13

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3887. Min Act: -0.0000

Data Index: 102743 (The Pile)

Max Activating Token Index: 906

Text #14

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3649. Min Act: -0.0000

Data Index: 791186 (The Pile)

Max Activating Token Index: 180

Text #15

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3529. Min Act: -0.0000

Data Index: 315882 (The Pile)

Max Activating Token Index: 235

Text #16

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3710. Min Act: -0.0000

Data Index: 395724 (The Pile)

Max Activating Token Index: 374

Text #17

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3634. Min Act: -0.0000

Data Index: 215565 (The Pile)

Max Activating Token Index: 179

Text #18

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1429590 (The Pile)

Max Activating Token Index: 534

Text #19

Max Range: 0.4961. Min Range: -0.4961

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1918676 (The Pile)

Max Activating Token Index: 332