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

Dataset: The Pile

Neuron 1523 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: 0.3264. Min Range: -0.3264

Max Act: 0.3264. Min Act: -0.0000

Data Index: 873427 (The Pile)

Max Activating Token Index: 1014

Text #1

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.3118. Min Act: -0.0000

Data Index: 1052348 (The Pile)

Max Activating Token Index: 974

Text #2

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2971. Min Act: -0.0000

Data Index: 1749126 (The Pile)

Max Activating Token Index: 646

Text #3

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2741. Min Act: -0.0000

Data Index: 545699 (The Pile)

Max Activating Token Index: 814

Text #4

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2588. Min Act: -0.0000

Data Index: 1303130 (The Pile)

Max Activating Token Index: 743

Text #5

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1206986 (The Pile)

Max Activating Token Index: 611

Text #6

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2470. Min Act: 0.0000

Data Index: 1583271 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1173343 (The Pile)

Max Activating Token Index: 377

Text #8

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2252. Min Act: -0.0000

Data Index: 707440 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2318. Min Act: -0.0000

Data Index: 1626927 (The Pile)

Max Activating Token Index: 879

Text #10

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2423. Min Act: -0.0000

Data Index: 711533 (The Pile)

Max Activating Token Index: 780

Text #11

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1313434 (The Pile)

Max Activating Token Index: 956

Text #12

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2317. Min Act: -0.0000

Data Index: 881231 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2312. Min Act: -0.0000

Data Index: 286308 (The Pile)

Max Activating Token Index: 248

Text #14

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1852391 (The Pile)

Max Activating Token Index: 710

Text #15

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2231. Min Act: -0.0000

Data Index: 922527 (The Pile)

Max Activating Token Index: 535

Text #16

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1304714 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2227. Min Act: -0.0000

Data Index: 599904 (The Pile)

Max Activating Token Index: 532

Text #18

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2024. Min Act: -0.0000

Data Index: 194174 (The Pile)

Max Activating Token Index: 724

Text #19

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2062. Min Act: -0.0000

Data Index: 271625 (The Pile)

Max Activating Token Index: 920