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

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

Neuron 60 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0035. Min Range: -1.0035

Max Act: 1.0035. Min Act: -0.0000

Data Index: 324373 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.8398. Min Act: -0.0000

Data Index: 593049 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7257. Min Act: -0.0000

Data Index: 503313 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7431. Min Act: -0.0000

Data Index: 481047 (C4 (Web Text))

Max Activating Token Index: 140

Text #4

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7547. Min Act: -0.0000

Data Index: 34144 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7275. Min Act: -0.0000

Data Index: 552706 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7033. Min Act: -0.0000

Data Index: 637682 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.6816. Min Act: -0.0000

Data Index: 304978 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.6363. Min Act: -0.0000

Data Index: 196590 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1292729 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1128416 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.6105. Min Act: -0.0000

Data Index: 13944 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.6348. Min Act: -0.0000

Data Index: 64209 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.6294. Min Act: -0.0000

Data Index: 259015 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.5822. Min Act: -0.0000

Data Index: 226683 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1280631 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.6260. Min Act: -0.0000

Data Index: 662271 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.5957. Min Act: -0.0000

Data Index: 671486 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.5729. Min Act: -0.0001

Data Index: 804580 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 1.0035. Min Range: -1.0035

Max Act: 0.5555. Min Act: -0.0001

Data Index: 266252 (C4 (Web Text))

Max Activating Token Index: 220