Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 414 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2406. Min Range: -1.2406

Max Act: 1.2406. Min Act: -0.0003

Data Index: 931008 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 1.2406. Min Range: -1.2406

Max Act: 1.0438. Min Act: -0.0003

Data Index: 273375 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.9794. Min Act: -0.0003

Data Index: 1051188 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.9704. Min Act: -0.0003

Data Index: 65928 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.8769. Min Act: -0.0003

Data Index: 808096 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.8748. Min Act: -0.0003

Data Index: 843184 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.8248. Min Act: -0.0003

Data Index: 1243515 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.8413. Min Act: -0.0003

Data Index: 582192 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.7718. Min Act: -0.0003

Data Index: 600656 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.7682. Min Act: -0.0003

Data Index: 969594 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.7924. Min Act: -0.0003

Data Index: 310867 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.7675. Min Act: -0.0003

Data Index: 1001523 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.7602. Min Act: -0.0003

Data Index: 77999 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.7568. Min Act: -0.0003

Data Index: 458989 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.7445. Min Act: -0.0003

Data Index: 1311052 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.7440. Min Act: -0.0003

Data Index: 10484 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.7676. Min Act: -0.0003

Data Index: 12299 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.7429. Min Act: -0.0003

Data Index: 1082442 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.7124. Min Act: -0.0003

Data Index: 979677 (C4 (Web Text))

Max Activating Token Index: 849

Text #19

Max Range: 1.2406. Min Range: -1.2406

Max Act: 0.7296. Min Act: -0.0003

Data Index: 119474 (C4 (Web Text))

Max Activating Token Index: 872