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

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

Neuron 4675 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.4336. Min Act: -0.0000

Data Index: 770757 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3888. Min Act: -0.0000

Data Index: 537232 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3765. Min Act: -0.0000

Data Index: 109337 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3487. Min Act: -0.0000

Data Index: 657881 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1255031 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3251. Min Act: -0.0000

Data Index: 102747 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3446. Min Act: -0.0000

Data Index: 1045494 (C4 (Web Text))

Max Activating Token Index: 785

Text #7

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3379. Min Act: -0.0000

Data Index: 376272 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3393. Min Act: -0.0000

Data Index: 391180 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3096. Min Act: -0.0000

Data Index: 808735 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1324220 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1029795 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.2812. Min Act: -0.0000

Data Index: 166327 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3128. Min Act: -0.0000

Data Index: 1057561 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.2918. Min Act: -0.0000

Data Index: 698938 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.2764. Min Act: -0.0001

Data Index: 825763 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3134. Min Act: -0.0000

Data Index: 498813 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.2919. Min Act: -0.0000

Data Index: 145159 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.3118. Min Act: -0.0000

Data Index: 773166 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.4336. Min Range: -0.4336

Max Act: 0.2821. Min Act: -0.0000

Data Index: 427182 (C4 (Web Text))

Max Activating Token Index: 276