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

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

Neuron 4999 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0485. Min Act: -0.0002

Data Index: 467530 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0488. Min Act: -0.0002

Data Index: 730460 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0460. Min Act: -0.0002

Data Index: 918293 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0447. Min Act: -0.0002

Data Index: 323765 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0422. Min Act: -0.0002

Data Index: 454729 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1094935 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0371. Min Act: -0.0002

Data Index: 626711 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0363. Min Act: -0.0002

Data Index: 76939 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1311377 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0383. Min Act: -0.0002

Data Index: 726767 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0432. Min Act: -0.0002

Data Index: 625863 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1108719 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0446. Min Act: -0.0002

Data Index: 871776 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0379. Min Act: -0.0002

Data Index: 901464 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0425. Min Act: -0.0002

Data Index: 666855 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0411. Min Act: -0.0002

Data Index: 850550 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0356. Min Act: -0.0002

Data Index: 74093 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0391. Min Act: -0.0002

Data Index: 668113 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1035960 (C4 (Web Text))

Max Activating Token Index: 246

Text #19

Max Range: 0.0488. Min Range: -0.0488

Max Act: 0.0377. Min Act: -0.0002

Data Index: 527169 (C4 (Web Text))

Max Activating Token Index: 951