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

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

Neuron 396 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: 1.4382. Min Range: -1.4382

Max Act: 1.3565. Min Act: -0.0000

Data Index: 472945 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.4382. Min Act: -0.0000

Data Index: 620458 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2880. Min Act: -0.0000

Data Index: 1073886 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.1407. Min Act: -0.0000

Data Index: 1069841 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2683. Min Act: -0.0000

Data Index: 1311007 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2386. Min Act: -0.0000

Data Index: 256440 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.1356. Min Act: -0.0001

Data Index: 1225275 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.3109. Min Act: -0.0000

Data Index: 324378 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.0979. Min Act: -0.0000

Data Index: 522985 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.0559. Min Act: -0.0000

Data Index: 1313466 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.0587. Min Act: -0.0000

Data Index: 934875 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.0149. Min Act: -0.0000

Data Index: 784305 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.0599. Min Act: -0.0000

Data Index: 749239 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 1.4382. Min Range: -1.4382

Max Act: 0.9823. Min Act: -0.0000

Data Index: 977203 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.0527. Min Act: -0.0000

Data Index: 1028547 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.0915. Min Act: -0.0000

Data Index: 144944 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.0206. Min Act: -0.0000

Data Index: 279456 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.0559. Min Act: -0.0000

Data Index: 864175 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 1.4382. Min Range: -1.4382

Max Act: 0.9616. Min Act: -0.0000

Data Index: 1078601 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.0159. Min Act: -0.0000

Data Index: 809793 (C4 (Web Text))

Max Activating Token Index: 891