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

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

Neuron 3656 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8883. Min Act: -0.0000

Data Index: 6020 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.9414. Min Act: -0.0000

Data Index: 353939 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.9219. Min Act: -0.0000

Data Index: 503122 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8661. Min Act: -0.0000

Data Index: 573360 (C4 (Web Text))

Max Activating Token Index: 224

Text #4

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8834. Min Act: -0.0000

Data Index: 503194 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7511. Min Act: -0.0000

Data Index: 814120 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8182. Min Act: -0.0000

Data Index: 1047146 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1272257 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1132508 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7727. Min Act: -0.0000

Data Index: 649749 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7686. Min Act: -0.0000

Data Index: 579181 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7951. Min Act: -0.0000

Data Index: 681551 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8180. Min Act: -0.0000

Data Index: 736171 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7621. Min Act: -0.0000

Data Index: 1080301 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.8223. Min Act: -0.0000

Data Index: 440957 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7828. Min Act: -0.0000

Data Index: 32732 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7312. Min Act: -0.0000

Data Index: 325986 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1007942 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7390. Min Act: -0.0000

Data Index: 267501 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 0.9414. Min Range: -0.9414

Max Act: 0.7498. Min Act: -0.0000

Data Index: 589477 (C4 (Web Text))

Max Activating Token Index: 785