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

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

Neuron 2326 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: 2.3430. Min Range: -2.3430

Max Act: 2.3430. Min Act: -0.0000

Data Index: 1285309 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 2.3430. Min Range: -2.3430

Max Act: 2.1496. Min Act: -0.0000

Data Index: 534408 (C4 (Web Text))

Max Activating Token Index: 886

Text #2

Max Range: 2.3430. Min Range: -2.3430

Max Act: 2.1524. Min Act: -0.0000

Data Index: 917547 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 2.3430. Min Range: -2.3430

Max Act: 2.0508. Min Act: -0.0000

Data Index: 157942 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.9602. Min Act: -0.0000

Data Index: 332771 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.8072. Min Act: -0.0000

Data Index: 826355 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.8361. Min Act: -0.0000

Data Index: 1077526 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.6649. Min Act: -0.0000

Data Index: 564490 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.7063. Min Act: -0.0000

Data Index: 1278971 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.8935. Min Act: -0.0000

Data Index: 535129 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.8583. Min Act: -0.0000

Data Index: 521565 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.7406. Min Act: -0.0000

Data Index: 469636 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.9104. Min Act: -0.0000

Data Index: 271229 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.8326. Min Act: -0.0000

Data Index: 1078412 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.4190. Min Act: -0.0000

Data Index: 754840 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.5712. Min Act: -0.0000

Data Index: 151815 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.6285. Min Act: -0.0000

Data Index: 185730 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.7000. Min Act: -0.0000

Data Index: 1311291 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.6209. Min Act: -0.0001

Data Index: 1215541 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 2.3430. Min Range: -2.3430

Max Act: 1.5085. Min Act: -0.0000

Data Index: 989565 (C4 (Web Text))

Max Activating Token Index: 231