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

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

Neuron 2327 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: 0.5027. Min Range: -0.5027

Max Act: 0.5027. Min Act: -0.0000

Data Index: 563686 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4693. Min Act: -0.0000

Data Index: 277653 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4426. Min Act: -0.0000

Data Index: 47566 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.4323. Min Act: -0.0001

Data Index: 371780 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3848. Min Act: -0.0000

Data Index: 24803 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1234339 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3828. Min Act: -0.0000

Data Index: 286687 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3534. Min Act: -0.0000

Data Index: 28688 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3742. Min Act: -0.0001

Data Index: 462016 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3679. Min Act: -0.0001

Data Index: 1088965 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3566. Min Act: -0.0000

Data Index: 345616 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3391. Min Act: -0.0001

Data Index: 190241 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3457. Min Act: -0.0000

Data Index: 1258759 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3329. Min Act: -0.0000

Data Index: 917699 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3411. Min Act: -0.0001

Data Index: 591016 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3380. Min Act: -0.0000

Data Index: 575678 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3304. Min Act: -0.0001

Data Index: 44914 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3201. Min Act: -0.0000

Data Index: 1113226 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3266. Min Act: -0.0000

Data Index: 213595 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.5027. Min Range: -0.5027

Max Act: 0.3032. Min Act: -0.0001

Data Index: 489114 (C4 (Web Text))

Max Activating Token Index: 691