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

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

Neuron 1540 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: 1.6371. Min Range: -1.6371

Max Act: 1.6371. Min Act: -0.0000

Data Index: 882181 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 1.6371. Min Range: -1.6371

Max Act: 1.2449. Min Act: -0.0000

Data Index: 467663 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 1.6371. Min Range: -1.6371

Max Act: 1.1738. Min Act: -0.0000

Data Index: 96923 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.9113. Min Act: -0.0000

Data Index: 469694 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.7603. Min Act: -0.0000

Data Index: 1086844 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.9460. Min Act: -0.0001

Data Index: 554264 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.7355. Min Act: -0.0001

Data Index: 882296 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.7530. Min Act: -0.0001

Data Index: 537972 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.7446. Min Act: -0.0000

Data Index: 408882 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.6361. Min Act: -0.0000

Data Index: 100147 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.7407. Min Act: -0.0000

Data Index: 250467 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.7203. Min Act: -0.0001

Data Index: 752166 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.5436. Min Act: -0.0000

Data Index: 530265 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.6662. Min Act: -0.0001

Data Index: 1346817 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1130364 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.6886. Min Act: -0.0000

Data Index: 470561 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.6638. Min Act: -0.0001

Data Index: 717531 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.7745. Min Act: -0.0000

Data Index: 1334250 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1173031 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 1.6371. Min Range: -1.6371

Max Act: 0.5841. Min Act: -0.0000

Data Index: 776067 (C4 (Web Text))

Max Activating Token Index: 365