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

Dataset: The Pile

Neuron 2982 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: 1.5479. Min Range: -1.5479

Max Act: 1.5479. Min Act: -0.0000

Data Index: 1407703 (The Pile)

Max Activating Token Index: 628

Text #1

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.4752. Min Act: -0.0000

Data Index: 973861 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.3385. Min Act: -0.0000

Data Index: 1996303 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.2960. Min Act: -0.0000

Data Index: 241734 (The Pile)

Max Activating Token Index: 431

Text #4

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.2292. Min Act: -0.0000

Data Index: 232427 (The Pile)

Max Activating Token Index: 59

Text #5

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.2330. Min Act: -0.0000

Data Index: 517528 (The Pile)

Max Activating Token Index: 320

Text #6

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.0913. Min Act: -0.0000

Data Index: 1194572 (The Pile)

Max Activating Token Index: 1019

Text #7

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.2133. Min Act: -0.0000

Data Index: 740297 (The Pile)

Max Activating Token Index: 27

Text #8

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.2839. Min Act: -0.0000

Data Index: 1643942 (The Pile)

Max Activating Token Index: 477

Text #9

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.2078. Min Act: -0.0000

Data Index: 802430 (The Pile)

Max Activating Token Index: 233

Text #10

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.0704. Min Act: -0.0000

Data Index: 690953 (The Pile)

Max Activating Token Index: 886

Text #11

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.1909. Min Act: -0.0000

Data Index: 312412 (The Pile)

Max Activating Token Index: 749

Text #12

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.1858. Min Act: -0.0000

Data Index: 1740024 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1572492 (The Pile)

Max Activating Token Index: 263

Text #14

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.1233. Min Act: -0.0000

Data Index: 360804 (The Pile)

Max Activating Token Index: 207

Text #15

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.1401. Min Act: -0.0000

Data Index: 1043107 (The Pile)

Max Activating Token Index: 575

Text #16

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.0006. Min Act: -0.0000

Data Index: 306474 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.0571. Min Act: -0.0000

Data Index: 291479 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.1267. Min Act: -0.0000

Data Index: 1163294 (The Pile)

Max Activating Token Index: 84

Text #19

Max Range: 1.5479. Min Range: -1.5479

Max Act: 1.1270. Min Act: -0.0000

Data Index: 1956171 (The Pile)

Max Activating Token Index: 155