Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 546 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.3613. Min Act: -0.0001

Data Index: 900854 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.1794. Min Act: -0.0001

Data Index: 797951 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.1805. Min Act: -0.0001

Data Index: 38618 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.0890. Min Act: -0.0001

Data Index: 750927 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.9515. Min Act: -0.0001

Data Index: 1266294 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.0258. Min Act: -0.0001

Data Index: 502435 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.0446. Min Act: -0.0001

Data Index: 43548 (C4 (Web Text))

Max Activating Token Index: 586

Text #7

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.0225. Min Act: -0.0001

Data Index: 178461 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.1057. Min Act: -0.0001

Data Index: 770773 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.9687. Min Act: -0.0002

Data Index: 952493 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 1.3613. Min Range: -1.3613

Max Act: 1.0481. Min Act: -0.0001

Data Index: 519957 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.9208. Min Act: -0.0001

Data Index: 153861 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.9749. Min Act: -0.0001

Data Index: 66976 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.9551. Min Act: -0.0001

Data Index: 140102 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.9364. Min Act: -0.0001

Data Index: 137369 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.9574. Min Act: -0.0001

Data Index: 1328986 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.9276. Min Act: -0.0001

Data Index: 274547 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.8768. Min Act: -0.0002

Data Index: 695850 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.9357. Min Act: -0.0001

Data Index: 376395 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 1.3613. Min Range: -1.3613

Max Act: 0.8709. Min Act: -0.0001

Data Index: 562402 (C4 (Web Text))

Max Activating Token Index: 633