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

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

Neuron 3144 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.4940. Min Act: -0.0000

Data Index: 940127 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.4245. Min Act: -0.0000

Data Index: 1328423 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3804. Min Act: -0.0000

Data Index: 235122 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3642. Min Act: -0.0000

Data Index: 308291 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3463. Min Act: -0.0000

Data Index: 372301 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3584. Min Act: -0.0000

Data Index: 738678 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3570. Min Act: -0.0000

Data Index: 324593 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3550. Min Act: -0.0000

Data Index: 121283 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3317. Min Act: -0.0000

Data Index: 215729 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3273. Min Act: -0.0000

Data Index: 117193 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1029159 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3204. Min Act: -0.0000

Data Index: 859857 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3034. Min Act: -0.0000

Data Index: 478904 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3034. Min Act: -0.0000

Data Index: 1248404 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1066746 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1019995 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.2677. Min Act: -0.0000

Data Index: 332918 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.2947. Min Act: -0.0000

Data Index: 202657 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.2901. Min Act: -0.0000

Data Index: 818528 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 0.4940. Min Range: -0.4940

Max Act: 0.2812. Min Act: -0.0000

Data Index: 5625 (C4 (Web Text))

Max Activating Token Index: 1011