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

Dataset: The Pile

Neuron 3435 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.5138. Min Act: -0.0000

Data Index: 1626262 (The Pile)

Max Activating Token Index: 96

Text #1

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.1708. Min Act: -0.0000

Data Index: 1098709 (The Pile)

Max Activating Token Index: 1008

Text #2

Max Range: 3.5138. Min Range: -3.5138

Max Act: 3.2021. Min Act: -0.0000

Data Index: 1319928 (The Pile)

Max Activating Token Index: 519

Text #3

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.3876. Min Act: -0.0000

Data Index: 1959377 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.2952. Min Act: -0.0000

Data Index: 1986360 (The Pile)

Max Activating Token Index: 947

Text #5

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.4281. Min Act: -0.0000

Data Index: 1271599 (The Pile)

Max Activating Token Index: 210

Text #6

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.1215. Min Act: -0.0000

Data Index: 1603823 (The Pile)

Max Activating Token Index: 909

Text #7

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.2130. Min Act: -0.0000

Data Index: 402218 (The Pile)

Max Activating Token Index: 414

Text #8

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.1856. Min Act: -0.0000

Data Index: 18792 (The Pile)

Max Activating Token Index: 748

Text #9

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.2862. Min Act: -0.0000

Data Index: 321106 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 3.5138. Min Range: -3.5138

Max Act: 1.9911. Min Act: -0.0000

Data Index: 103498 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.1134. Min Act: -0.0000

Data Index: 429825 (The Pile)

Max Activating Token Index: 187

Text #12

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.3403. Min Act: -0.0000

Data Index: 1960236 (The Pile)

Max Activating Token Index: 722

Text #13

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.2306. Min Act: -0.0000

Data Index: 550790 (The Pile)

Max Activating Token Index: 746

Text #14

Max Range: 3.5138. Min Range: -3.5138

Max Act: 1.9687. Min Act: -0.0000

Data Index: 1209476 (The Pile)

Max Activating Token Index: 1020

Text #15

Max Range: 3.5138. Min Range: -3.5138

Max Act: 1.9371. Min Act: -0.0000

Data Index: 1767767 (The Pile)

Max Activating Token Index: 754

Text #16

Max Range: 3.5138. Min Range: -3.5138

Max Act: 1.8836. Min Act: -0.0000

Data Index: 1868970 (The Pile)

Max Activating Token Index: 844

Text #17

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.1123. Min Act: -0.0000

Data Index: 937499 (The Pile)

Max Activating Token Index: 447

Text #18

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.0111. Min Act: -0.0000

Data Index: 467393 (The Pile)

Max Activating Token Index: 131

Text #19

Max Range: 3.5138. Min Range: -3.5138

Max Act: 2.2140. Min Act: -0.0000

Data Index: 1699127 (The Pile)

Max Activating Token Index: 922