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

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

Neuron 5871 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3264. Min Range: -4.3264

Max Act: 4.3264. Min Act: -0.0000

Data Index: 1069160 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 4.3264. Min Range: -4.3264

Max Act: 4.2190. Min Act: -0.0000

Data Index: 1082992 (C4 (Web Text))

Max Activating Token Index: 587

Text #2

Max Range: 4.3264. Min Range: -4.3264

Max Act: 4.0447. Min Act: -0.0000

Data Index: 12963 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 4.3264. Min Range: -4.3264

Max Act: 4.1879. Min Act: -0.0000

Data Index: 773643 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 4.3264. Min Range: -4.3264

Max Act: 4.1575. Min Act: -0.0000

Data Index: 1112865 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 4.3264. Min Range: -4.3264

Max Act: 3.9736. Min Act: 0.0000

Data Index: 875617 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 4.3264. Min Range: -4.3264

Max Act: 4.1127. Min Act: 0.0000

Data Index: 622181 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 4.3264. Min Range: -4.3264

Max Act: 4.0929. Min Act: -0.0000

Data Index: 625141 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 4.3264. Min Range: -4.3264

Max Act: 4.0704. Min Act: -0.0000

Data Index: 357008 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 4.3264. Min Range: -4.3264

Max Act: 4.0982. Min Act: -0.0000

Data Index: 570758 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 4.3264. Min Range: -4.3264

Max Act: 4.0403. Min Act: -0.0000

Data Index: 206299 (C4 (Web Text))

Max Activating Token Index: 521

Text #11

Max Range: 4.3264. Min Range: -4.3264

Max Act: 4.0341. Min Act: -0.0000

Data Index: 1193874 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 4.3264. Min Range: -4.3264

Max Act: 4.0169. Min Act: -0.0000

Data Index: 278205 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 4.3264. Min Range: -4.3264

Max Act: 4.0035. Min Act: -0.0000

Data Index: 1216904 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 4.3264. Min Range: -4.3264

Max Act: 4.0057. Min Act: -0.0000

Data Index: 541228 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 4.3264. Min Range: -4.3264

Max Act: 4.1701. Min Act: 0.0000

Data Index: 1157292 (C4 (Web Text))

Max Activating Token Index: 341

Text #16

Max Range: 4.3264. Min Range: -4.3264

Max Act: 3.8913. Min Act: -0.0000

Data Index: 1286248 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 4.3264. Min Range: -4.3264

Max Act: 3.8925. Min Act: -0.0000

Data Index: 265309 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 4.3264. Min Range: -4.3264

Max Act: 3.8494. Min Act: 0.0000

Data Index: 647548 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 4.3264. Min Range: -4.3264

Max Act: 3.8470. Min Act: -0.0000

Data Index: 218127 (C4 (Web Text))

Max Activating Token Index: 646