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

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

Neuron 3814 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.4209. Min Act: -0.0001

Data Index: 906907 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.4184. Min Act: -0.0001

Data Index: 270506 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3979. Min Act: -0.0001

Data Index: 155971 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3759. Min Act: -0.0001

Data Index: 1197217 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3909. Min Act: -0.0001

Data Index: 1220118 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3945. Min Act: -0.0001

Data Index: 665522 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3709. Min Act: -0.0001

Data Index: 809058 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3801. Min Act: -0.0001

Data Index: 829400 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3883. Min Act: -0.0001

Data Index: 647831 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3720. Min Act: -0.0001

Data Index: 913279 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3796. Min Act: -0.0001

Data Index: 900214 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3871. Min Act: -0.0001

Data Index: 1273154 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3697. Min Act: -0.0001

Data Index: 243968 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3556. Min Act: -0.0001

Data Index: 354925 (C4 (Web Text))

Max Activating Token Index: 7

Text #14

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3683. Min Act: -0.0001

Data Index: 836432 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3422. Min Act: -0.0001

Data Index: 1232662 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3426. Min Act: -0.0001

Data Index: 595443 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3632. Min Act: -0.0001

Data Index: 1356676 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3511. Min Act: -0.0001

Data Index: 749944 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.4209. Min Range: -0.4209

Max Act: 0.3690. Min Act: -0.0001

Data Index: 1249650 (C4 (Web Text))

Max Activating Token Index: 153