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

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

Neuron 938 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.1416. Min Act: -0.0000

Data Index: 838376 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1194586 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0529. Min Act: -0.0000

Data Index: 191302 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0487. Min Act: -0.0000

Data Index: 198244 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0495. Min Act: -0.0000

Data Index: 644787 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0396. Min Act: -0.0000

Data Index: 129826 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0396. Min Act: -0.0000

Data Index: 1168807 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0431. Min Act: -0.0000

Data Index: 448256 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0451. Min Act: -0.0000

Data Index: 928602 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0435. Min Act: -0.0000

Data Index: 335763 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0433. Min Act: -0.0000

Data Index: 448664 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0447. Min Act: -0.0000

Data Index: 466489 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0447. Min Act: -0.0000

Data Index: 678732 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0433. Min Act: -0.0000

Data Index: 267195 (C4 (Web Text))

Max Activating Token Index: 292

Text #14

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0418. Min Act: -0.0000

Data Index: 1088161 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0386. Min Act: -0.0000

Data Index: 1177593 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0334. Min Act: -0.0000

Data Index: 684686 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0393. Min Act: -0.0000

Data Index: 324093 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0455. Min Act: -0.0000

Data Index: 908598 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.1416. Min Range: -0.1416

Max Act: 0.0389. Min Act: -0.0000

Data Index: 479281 (C4 (Web Text))

Max Activating Token Index: 778