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

Dataset: The Pile

Neuron 1178 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: 1.5884. Min Range: -1.5884

Max Act: 1.5884. Min Act: -0.0000

Data Index: 1575541 (The Pile)

Max Activating Token Index: 607

Text #1

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.1419. Min Act: -0.0000

Data Index: 798856 (The Pile)

Max Activating Token Index: 639

Text #2

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.0853. Min Act: -0.0000

Data Index: 256578 (The Pile)

Max Activating Token Index: 311

Text #3

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.1342. Min Act: -0.0000

Data Index: 1672435 (The Pile)

Max Activating Token Index: 226

Text #4

Max Range: 1.5884. Min Range: -1.5884

Max Act: 0.9962. Min Act: -0.0000

Data Index: 10694 (The Pile)

Max Activating Token Index: 680

Text #5

Max Range: 1.5884. Min Range: -1.5884

Max Act: 1.0537. Min Act: -0.0000

Data Index: 1072466 (The Pile)

Max Activating Token Index: 89

Text #6

Max Range: 1.5884. Min Range: -1.5884

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1585145 (The Pile)

Max Activating Token Index: 489

Text #7

Max Range: 1.5884. Min Range: -1.5884

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1037790 (The Pile)

Max Activating Token Index: 388

Text #8

Max Range: 1.5884. Min Range: -1.5884

Max Act: 0.9694. Min Act: -0.0000

Data Index: 444940 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 1.5884. Min Range: -1.5884

Max Act: 0.9299. Min Act: -0.0000

Data Index: 835613 (The Pile)

Max Activating Token Index: 756

Text #10

Max Range: 1.5884. Min Range: -1.5884

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1506175 (The Pile)

Max Activating Token Index: 640

Text #11

Max Range: 1.5884. Min Range: -1.5884

Max Act: 0.8736. Min Act: -0.0000

Data Index: 546230 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 1.5884. Min Range: -1.5884

Max Act: 0.9636. Min Act: -0.0000

Data Index: 741102 (The Pile)

Max Activating Token Index: 844

Text #13

Max Range: 1.5884. Min Range: -1.5884

Max Act: 0.7840. Min Act: 0.0000

Data Index: 1383068 (The Pile)

Max Activating Token Index: 131

Text #14

Max Range: 1.5884. Min Range: -1.5884

Max Act: 0.8715. Min Act: -0.0000

Data Index: 233601 (The Pile)

Max Activating Token Index: 523

Text #15

Max Range: 1.5884. Min Range: -1.5884

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1202947 (The Pile)

Max Activating Token Index: 182

Text #16

Max Range: 1.5884. Min Range: -1.5884

Max Act: 0.8263. Min Act: -0.0000

Data Index: 454071 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 1.5884. Min Range: -1.5884

Max Act: 0.8655. Min Act: -0.0000

Data Index: 811026 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 1.5884. Min Range: -1.5884

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1499270 (The Pile)

Max Activating Token Index: 574

Text #19

Max Range: 1.5884. Min Range: -1.5884

Max Act: 0.7627. Min Act: -0.0000

Data Index: 209054 (The Pile)

Max Activating Token Index: 171