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

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

Neuron 5533 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.8511. Min Act: -0.0000

Data Index: 528312 (C4 (Web Text))

Max Activating Token Index: 255

Text #1

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.8491. Min Act: -0.0000

Data Index: 53534 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7182. Min Act: -0.0000

Data Index: 610366 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7099. Min Act: -0.0000

Data Index: 890227 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1099910 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6636. Min Act: -0.0000

Data Index: 461313 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1149381 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6699. Min Act: -0.0000

Data Index: 946437 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.5793. Min Act: -0.0000

Data Index: 950436 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.5733. Min Act: -0.0000

Data Index: 454322 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.5720. Min Act: -0.0000

Data Index: 778327 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.5518. Min Act: -0.0000

Data Index: 184664 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.5756. Min Act: -0.0000

Data Index: 230036 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.5266. Min Act: -0.0000

Data Index: 901792 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1014256 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1089331 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.5790. Min Act: -0.0000

Data Index: 118007 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.5693. Min Act: -0.0000

Data Index: 734939 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1251484 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1211510 (C4 (Web Text))

Max Activating Token Index: 892