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

Dataset: The Pile

Neuron 2563 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: 0.7028. Min Range: -0.7028

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1501043 (The Pile)

Max Activating Token Index: 273

Text #1

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.6933. Min Act: -0.0000

Data Index: 552345 (The Pile)

Max Activating Token Index: 199

Text #2

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.7028. Min Act: -0.0000

Data Index: 772660 (The Pile)

Max Activating Token Index: 155

Text #3

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1623017 (The Pile)

Max Activating Token Index: 304

Text #4

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.5786. Min Act: -0.0000

Data Index: 140185 (The Pile)

Max Activating Token Index: 687

Text #5

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.5500. Min Act: -0.0000

Data Index: 141945 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.5859. Min Act: -0.0000

Data Index: 367897 (The Pile)

Max Activating Token Index: 735

Text #7

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.5634. Min Act: -0.0000

Data Index: 27049 (The Pile)

Max Activating Token Index: 965

Text #8

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1383517 (The Pile)

Max Activating Token Index: 822

Text #9

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.5933. Min Act: -0.0000

Data Index: 729315 (The Pile)

Max Activating Token Index: 467

Text #10

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.5563. Min Act: -0.0000

Data Index: 345994 (The Pile)

Max Activating Token Index: 264

Text #11

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1318028 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1980088 (The Pile)

Max Activating Token Index: 339

Text #13

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.5233. Min Act: -0.0000

Data Index: 8324 (The Pile)

Max Activating Token Index: 453

Text #14

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.5149. Min Act: -0.0000

Data Index: 1068875 (The Pile)

Max Activating Token Index: 924

Text #15

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1318852 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.5253. Min Act: -0.0000

Data Index: 28545 (The Pile)

Max Activating Token Index: 125

Text #17

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.5235. Min Act: -0.0000

Data Index: 542272 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1095637 (The Pile)

Max Activating Token Index: 147

Text #19

Max Range: 0.7028. Min Range: -0.7028

Max Act: 0.5916. Min Act: -0.0000

Data Index: 297599 (The Pile)

Max Activating Token Index: 296