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

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

Neuron 5092 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: 1.2548. Min Range: -1.2548

Max Act: 1.2548. Min Act: -0.0001

Data Index: 857836 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.2548. Min Range: -1.2548

Max Act: 1.0115. Min Act: -0.0001

Data Index: 601406 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.2548. Min Range: -1.2548

Max Act: 1.0555. Min Act: -0.0001

Data Index: 1279400 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.9299. Min Act: -0.0001

Data Index: 1313839 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.9225. Min Act: -0.0001

Data Index: 1007740 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.9291. Min Act: -0.0001

Data Index: 704867 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.8661. Min Act: -0.0001

Data Index: 401648 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.8984. Min Act: -0.0001

Data Index: 515631 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.9098. Min Act: -0.0001

Data Index: 726250 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.8321. Min Act: -0.0001

Data Index: 1264577 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.9315. Min Act: -0.0001

Data Index: 173578 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.9046. Min Act: -0.0001

Data Index: 104494 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.9352. Min Act: -0.0001

Data Index: 1054236 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.8740. Min Act: -0.0001

Data Index: 1123093 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.8336. Min Act: -0.0001

Data Index: 1159091 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.8822. Min Act: -0.0001

Data Index: 1121987 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.8368. Min Act: -0.0001

Data Index: 343643 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.7988. Min Act: -0.0001

Data Index: 196293 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.9308. Min Act: -0.0001

Data Index: 630566 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 1.2548. Min Range: -1.2548

Max Act: 0.8526. Min Act: -0.0001

Data Index: 792411 (C4 (Web Text))

Max Activating Token Index: 613