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

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

Neuron 582 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4748. Min Act: -0.0001

Data Index: 1099418 (C4 (Web Text))

Max Activating Token Index: 167

Text #1

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4388. Min Act: -0.0000

Data Index: 478925 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4234. Min Act: -0.0000

Data Index: 822801 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3668. Min Act: -0.0000

Data Index: 252573 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3573. Min Act: -0.0000

Data Index: 765346 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3627. Min Act: -0.0000

Data Index: 594688 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3708. Min Act: -0.0000

Data Index: 794506 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3264. Min Act: -0.0001

Data Index: 655789 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3429. Min Act: -0.0000

Data Index: 141925 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3730. Min Act: -0.0001

Data Index: 384967 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3200. Min Act: -0.0001

Data Index: 837300 (C4 (Web Text))

Max Activating Token Index: 943

Text #11

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3257. Min Act: -0.0000

Data Index: 407332 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3368. Min Act: -0.0000

Data Index: 272656 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3579. Min Act: -0.0000

Data Index: 534565 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3259. Min Act: -0.0000

Data Index: 184185 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3022. Min Act: -0.0000

Data Index: 384379 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3218. Min Act: -0.0000

Data Index: 71058 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1128159 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3049. Min Act: -0.0000

Data Index: 1295597 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.2951. Min Act: -0.0000

Data Index: 433218 (C4 (Web Text))

Max Activating Token Index: 1019