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

Dataset: The Pile

Neuron 779 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: 1.1200. Min Range: -1.1200

Max Act: 1.1200. Min Act: -0.0000

Data Index: 1521611 (The Pile)

Max Activating Token Index: 976

Text #1

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1505264 (The Pile)

Max Activating Token Index: 656

Text #2

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5362. Min Act: -0.0000

Data Index: 472485 (The Pile)

Max Activating Token Index: 565

Text #3

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5355. Min Act: -0.0000

Data Index: 351239 (The Pile)

Max Activating Token Index: 233

Text #4

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1167345 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.4992. Min Act: -0.0000

Data Index: 952978 (The Pile)

Max Activating Token Index: 722

Text #6

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5399. Min Act: -0.0000

Data Index: 646537 (The Pile)

Max Activating Token Index: 570

Text #7

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5354. Min Act: -0.0000

Data Index: 46317 (The Pile)

Max Activating Token Index: 877

Text #8

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5157. Min Act: -0.0000

Data Index: 716616 (The Pile)

Max Activating Token Index: 400

Text #9

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1513018 (The Pile)

Max Activating Token Index: 352

Text #10

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5013. Min Act: -0.0000

Data Index: 805056 (The Pile)

Max Activating Token Index: 247

Text #11

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5093. Min Act: -0.0000

Data Index: 961056 (The Pile)

Max Activating Token Index: 886

Text #12

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.4560. Min Act: -0.0000

Data Index: 572350 (The Pile)

Max Activating Token Index: 909

Text #13

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1323715 (The Pile)

Max Activating Token Index: 844

Text #14

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.4273. Min Act: -0.0000

Data Index: 9970 (The Pile)

Max Activating Token Index: 380

Text #15

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1423454 (The Pile)

Max Activating Token Index: 962

Text #16

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.4192. Min Act: -0.0000

Data Index: 98797 (The Pile)

Max Activating Token Index: 458

Text #17

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.4611. Min Act: -0.0000

Data Index: 868780 (The Pile)

Max Activating Token Index: 1001

Text #18

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1835130 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 1.1200. Min Range: -1.1200

Max Act: 0.4446. Min Act: -0.0000

Data Index: 1422052 (The Pile)

Max Activating Token Index: 1010