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

Dataset: The Pile

Neuron 2615 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: 0.3954. Min Range: -0.3954

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1194152 (The Pile)

Max Activating Token Index: 195

Text #1

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2806. Min Act: -0.0000

Data Index: 476964 (The Pile)

Max Activating Token Index: 56

Text #2

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1053786 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2697. Min Act: -0.0000

Data Index: 869783 (The Pile)

Max Activating Token Index: 495

Text #4

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2194. Min Act: -0.0000

Data Index: 956580 (The Pile)

Max Activating Token Index: 694

Text #5

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2713. Min Act: -0.0000

Data Index: 124090 (The Pile)

Max Activating Token Index: 298

Text #6

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2507. Min Act: -0.0000

Data Index: 22506 (The Pile)

Max Activating Token Index: 333

Text #7

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2303. Min Act: -0.0000

Data Index: 509743 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2355. Min Act: -0.0000

Data Index: 117067 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1898018 (The Pile)

Max Activating Token Index: 54

Text #10

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1679250 (The Pile)

Max Activating Token Index: 406

Text #11

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.1714. Min Act: -0.0000

Data Index: 2629 (The Pile)

Max Activating Token Index: 502

Text #12

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1068907 (The Pile)

Max Activating Token Index: 882

Text #13

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2246. Min Act: -0.0000

Data Index: 58884 (The Pile)

Max Activating Token Index: 469

Text #14

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2177. Min Act: -0.0000

Data Index: 432152 (The Pile)

Max Activating Token Index: 743

Text #15

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2216. Min Act: -0.0000

Data Index: 184643 (The Pile)

Max Activating Token Index: 203

Text #16

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1780562 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1404393 (The Pile)

Max Activating Token Index: 206

Text #18

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2248. Min Act: -0.0000

Data Index: 1622376 (The Pile)

Max Activating Token Index: 244

Text #19

Max Range: 0.3954. Min Range: -0.3954

Max Act: 0.2308. Min Act: -0.0000

Data Index: 494737 (The Pile)

Max Activating Token Index: 909