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

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

Neuron 1826 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: 1.5919. Min Range: -1.5919

Max Act: 1.5919. Min Act: -0.0000

Data Index: 512403 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.3257. Min Act: -0.0000

Data Index: 1041557 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.3384. Min Act: -0.0000

Data Index: 86945 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.3275. Min Act: -0.0000

Data Index: 906133 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.3188. Min Act: -0.0000

Data Index: 252324 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2642. Min Act: -0.0000

Data Index: 280418 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2598. Min Act: -0.0000

Data Index: 1330647 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2216. Min Act: -0.0000

Data Index: 917582 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2398. Min Act: -0.0000

Data Index: 795581 (C4 (Web Text))

Max Activating Token Index: 454

Text #9

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1878. Min Act: -0.0000

Data Index: 592860 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2153. Min Act: -0.0000

Data Index: 1060680 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2516. Min Act: -0.0000

Data Index: 68437 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2053. Min Act: -0.0000

Data Index: 388716 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1673. Min Act: -0.0000

Data Index: 1427451 (Python Code)

Max Activating Token Index: 439

Text #14

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1972. Min Act: -0.0000

Data Index: 456587 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1999. Min Act: -0.0000

Data Index: 551878 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1581. Min Act: -0.0000

Data Index: 833274 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2298. Min Act: -0.0000

Data Index: 560813 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.2237. Min Act: -0.0000

Data Index: 378270 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 1.5919. Min Range: -1.5919

Max Act: 1.1486. Min Act: -0.0000

Data Index: 731491 (C4 (Web Text))

Max Activating Token Index: 497