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

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

Neuron 1520 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: 0.0751. Min Range: -0.0751

Max Act: 0.0751. Min Act: -0.0003

Data Index: 1349401 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0672. Min Act: -0.0003

Data Index: 195054 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0614. Min Act: -0.0003

Data Index: 850829 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0517. Min Act: -0.0003

Data Index: 762026 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0567. Min Act: -0.0003

Data Index: 469692 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0557. Min Act: -0.0002

Data Index: 238339 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0549. Min Act: -0.0003

Data Index: 495645 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0541. Min Act: -0.0003

Data Index: 463851 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0552. Min Act: -0.0003

Data Index: 1221572 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0537. Min Act: -0.0003

Data Index: 67164 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0535. Min Act: -0.0003

Data Index: 870820 (C4 (Web Text))

Max Activating Token Index: 440

Text #11

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0537. Min Act: -0.0003

Data Index: 743686 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0496. Min Act: -0.0003

Data Index: 707319 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0517. Min Act: -0.0003

Data Index: 653953 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0514. Min Act: -0.0002

Data Index: 511177 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0459. Min Act: -0.0003

Data Index: 558928 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0454. Min Act: -0.0003

Data Index: 338582 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1126612 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0490. Min Act: -0.0003

Data Index: 1336709 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0470. Min Act: -0.0003

Data Index: 392545 (C4 (Web Text))

Max Activating Token Index: 243