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

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

Neuron 2878 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.9159. Min Act: -0.0000

Data Index: 81106 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.9379. Min Act: -0.0000

Data Index: 220607 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.9169. Min Act: -0.0000

Data Index: 1146466 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.8655. Min Act: -0.0000

Data Index: 703968 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.5496. Min Act: -0.0000

Data Index: 717467 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.5358. Min Act: -0.0000

Data Index: 1405409 (Python Code)

Max Activating Token Index: 354

Text #6

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.3022. Min Act: 0.0000

Data Index: 421163 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.2645. Min Act: -0.0000

Data Index: 1126895 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.4031. Min Act: 0.0000

Data Index: 685 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.3785. Min Act: -0.0000

Data Index: 1367496 (Python Code)

Max Activating Token Index: 567

Text #10

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.5622. Min Act: 0.0000

Data Index: 1150319 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.5228. Min Act: 0.0000

Data Index: 984595 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.4310. Min Act: -0.0000

Data Index: 527908 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.2449. Min Act: -0.0000

Data Index: 74804 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.3931. Min Act: -0.0000

Data Index: 820856 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.1592. Min Act: -0.0000

Data Index: 1117876 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.2358. Min Act: 0.0000

Data Index: 663241 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 4.9379. Min Range: -4.9379

Max Act: 4.4097. Min Act: -0.0000

Data Index: 530900 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 4.9379. Min Range: -4.9379

Max Act: 3.6394. Min Act: -0.0000

Data Index: 122198 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 4.9379. Min Range: -4.9379

Max Act: 3.7338. Min Act: 0.0000

Data Index: 809825 (C4 (Web Text))

Max Activating Token Index: 844