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

Dataset: The Pile

Neuron 4991 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1079711 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1059432 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2617. Min Act: 0.0000

Data Index: 490131 (The Pile)

Max Activating Token Index: 74

Text #3

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2409. Min Act: -0.0000

Data Index: 320205 (The Pile)

Max Activating Token Index: 892

Text #4

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1731959 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2673. Min Act: -0.0000

Data Index: 197113 (The Pile)

Max Activating Token Index: 257

Text #6

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2431. Min Act: -0.0000

Data Index: 1051962 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2655. Min Act: -0.0000

Data Index: 978420 (The Pile)

Max Activating Token Index: 396

Text #8

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2492. Min Act: -0.0000

Data Index: 730429 (The Pile)

Max Activating Token Index: 236

Text #9

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2589. Min Act: -0.0000

Data Index: 1381211 (The Pile)

Max Activating Token Index: 710

Text #10

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2242. Min Act: 0.0000

Data Index: 719735 (The Pile)

Max Activating Token Index: 85

Text #11

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2456. Min Act: -0.0000

Data Index: 632399 (The Pile)

Max Activating Token Index: 71

Text #12

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2219. Min Act: -0.0000

Data Index: 1642348 (The Pile)

Max Activating Token Index: 1004

Text #13

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1738140 (The Pile)

Max Activating Token Index: 295

Text #14

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2334. Min Act: -0.0000

Data Index: 803973 (The Pile)

Max Activating Token Index: 291

Text #15

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2306. Min Act: -0.0000

Data Index: 176176 (The Pile)

Max Activating Token Index: 889

Text #16

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2270. Min Act: -0.0000

Data Index: 113256 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2222. Min Act: -0.0000

Data Index: 1004193 (The Pile)

Max Activating Token Index: 780

Text #18

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1352041 (The Pile)

Max Activating Token Index: 888

Text #19

Max Range: 0.2809. Min Range: -0.2809

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1433538 (The Pile)

Max Activating Token Index: 1021