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

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

Neuron 1725 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: 1.8270. Min Range: -1.8270

Max Act: 1.8270. Min Act: -0.0001

Data Index: 909200 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.3851. Min Act: -0.0001

Data Index: 365520 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.3494. Min Act: -0.0001

Data Index: 479905 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.3358. Min Act: -0.0001

Data Index: 491243 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.5706. Min Act: -0.0002

Data Index: 787999 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.3567. Min Act: -0.0002

Data Index: 93794 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.3670. Min Act: -0.0002

Data Index: 805192 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.2983. Min Act: -0.0001

Data Index: 560765 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.2325. Min Act: -0.0001

Data Index: 569221 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.4377. Min Act: -0.0001

Data Index: 294406 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.1634. Min Act: -0.0002

Data Index: 455771 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.0822. Min Act: -0.0001

Data Index: 636150 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.2453. Min Act: -0.0001

Data Index: 737412 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.1924. Min Act: -0.0001

Data Index: 338126 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.3746. Min Act: -0.0001

Data Index: 372576 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.2480. Min Act: -0.0001

Data Index: 687282 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.1309. Min Act: -0.0002

Data Index: 1056484 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.2347. Min Act: -0.0001

Data Index: 1007081 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.1690. Min Act: -0.0001

Data Index: 866 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 1.8270. Min Range: -1.8270

Max Act: 1.1743. Min Act: -0.0001

Data Index: 718996 (C4 (Web Text))

Max Activating Token Index: 631