Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4446 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6872. Min Act: -0.0000

Data Index: 1281316 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.6492. Min Act: -0.0000

Data Index: 722309 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.4708. Min Act: -0.0000

Data Index: 204358 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.4188. Min Act: -0.0000

Data Index: 529420 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.3094. Min Act: -0.0000

Data Index: 1167823 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.2236. Min Act: -0.0000

Data Index: 484097 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.2183. Min Act: -0.0000

Data Index: 672210 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.2784. Min Act: -0.0000

Data Index: 360828 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.2838. Min Act: -0.0000

Data Index: 1196556 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.2725. Min Act: -0.0000

Data Index: 931818 (C4 (Web Text))

Max Activating Token Index: 477

Text #10

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.2494. Min Act: -0.0000

Data Index: 1333351 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.2541. Min Act: -0.0000

Data Index: 85154 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.1659. Min Act: -0.0000

Data Index: 826675 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.2395. Min Act: -0.0000

Data Index: 146224 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.2949. Min Act: -0.0000

Data Index: 480833 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.2213. Min Act: -0.0000

Data Index: 588572 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.2137. Min Act: -0.0000

Data Index: 906889 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.1426. Min Act: -0.0000

Data Index: 805290 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.1357. Min Act: -0.0000

Data Index: 933875 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 1.6872. Min Range: -1.6872

Max Act: 1.2006. Min Act: -0.0000

Data Index: 98370 (C4 (Web Text))

Max Activating Token Index: 324