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

Dataset: The Pile

Neuron 1727 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: 1.2471. Min Range: -1.2471

Max Act: 1.2471. Min Act: 0.0000

Data Index: 1725795 (The Pile)

Max Activating Token Index: 905

Text #1

Max Range: 1.2471. Min Range: -1.2471

Max Act: 1.1055. Min Act: -0.0000

Data Index: 935464 (The Pile)

Max Activating Token Index: 458

Text #2

Max Range: 1.2471. Min Range: -1.2471

Max Act: 1.0787. Min Act: -0.0000

Data Index: 1572915 (The Pile)

Max Activating Token Index: 525

Text #3

Max Range: 1.2471. Min Range: -1.2471

Max Act: 1.0523. Min Act: -0.0000

Data Index: 1222865 (The Pile)

Max Activating Token Index: 104

Text #4

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.9948. Min Act: -0.0000

Data Index: 731128 (The Pile)

Max Activating Token Index: 88

Text #5

Max Range: 1.2471. Min Range: -1.2471

Max Act: 1.1124. Min Act: -0.0000

Data Index: 1324208 (The Pile)

Max Activating Token Index: 642

Text #6

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.9725. Min Act: -0.0000

Data Index: 88462 (The Pile)

Max Activating Token Index: 580

Text #7

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.9277. Min Act: 0.0000

Data Index: 181895 (The Pile)

Max Activating Token Index: 859

Text #8

Max Range: 1.2471. Min Range: -1.2471

Max Act: 1.1443. Min Act: 0.0000

Data Index: 620412 (The Pile)

Max Activating Token Index: 116

Text #9

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.8178. Min Act: -0.0000

Data Index: 547310 (The Pile)

Max Activating Token Index: 217

Text #10

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.9625. Min Act: -0.0000

Data Index: 1347077 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.9337. Min Act: 0.0000

Data Index: 1504314 (The Pile)

Max Activating Token Index: 735

Text #12

Max Range: 1.2471. Min Range: -1.2471

Max Act: 1.0145. Min Act: -0.0000

Data Index: 1262657 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.9020. Min Act: -0.0000

Data Index: 1341566 (The Pile)

Max Activating Token Index: 93

Text #14

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1481638 (The Pile)

Max Activating Token Index: 991

Text #15

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.9885. Min Act: -0.0000

Data Index: 787413 (The Pile)

Max Activating Token Index: 986

Text #16

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.9834. Min Act: -0.0000

Data Index: 390342 (The Pile)

Max Activating Token Index: 390

Text #17

Max Range: 1.2471. Min Range: -1.2471

Max Act: 1.0395. Min Act: 0.0000

Data Index: 308889 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.8126. Min Act: 0.0000

Data Index: 1094809 (The Pile)

Max Activating Token Index: 994

Text #19

Max Range: 1.2471. Min Range: -1.2471

Max Act: 0.8306. Min Act: 0.0000

Data Index: 1142380 (The Pile)

Max Activating Token Index: 216