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

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

Neuron 4642 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.9443. Min Act: -0.0000

Data Index: 498051 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.9216. Min Act: -0.0000

Data Index: 228447 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.8719. Min Act: -0.0000

Data Index: 685484 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.5725. Min Act: -0.0000

Data Index: 177820 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.6587. Min Act: -0.0000

Data Index: 198888 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.8807. Min Act: -0.0000

Data Index: 1241069 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.8019. Min Act: -0.0000

Data Index: 1079534 (C4 (Web Text))

Max Activating Token Index: 751

Text #7

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.6030. Min Act: -0.0000

Data Index: 1251193 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.6322. Min Act: -0.0001

Data Index: 1220643 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.6281. Min Act: -0.0000

Data Index: 864929 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.5592. Min Act: -0.0000

Data Index: 1336838 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.5533. Min Act: -0.0000

Data Index: 402349 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.6399. Min Act: -0.0000

Data Index: 538212 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.5465. Min Act: -0.0000

Data Index: 808797 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.4620. Min Act: -0.0000

Data Index: 954379 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.5320. Min Act: -0.0001

Data Index: 273166 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.5315. Min Act: -0.0000

Data Index: 1115990 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.4014. Min Act: -0.0000

Data Index: 1130480 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.4112. Min Act: -0.0000

Data Index: 601441 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 1.9443. Min Range: -1.9443

Max Act: 1.4006. Min Act: -0.0000

Data Index: 1329055 (C4 (Web Text))

Max Activating Token Index: 44