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

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

Neuron 4795 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: 0.3550. Min Range: -0.3550

Max Act: 0.3550. Min Act: -0.0000

Data Index: 774262 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3350. Min Act: -0.0000

Data Index: 348428 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3170. Min Act: -0.0000

Data Index: 1057911 (C4 (Web Text))

Max Activating Token Index: 933

Text #3

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3110. Min Act: -0.0000

Data Index: 991281 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3373. Min Act: -0.0000

Data Index: 819769 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3316. Min Act: -0.0000

Data Index: 424207 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3079. Min Act: -0.0000

Data Index: 213616 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3282. Min Act: -0.0000

Data Index: 622757 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3086. Min Act: -0.0000

Data Index: 267310 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1124812 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1270645 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3110. Min Act: -0.0000

Data Index: 891638 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1312431 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2983. Min Act: -0.0000

Data Index: 1336390 (C4 (Web Text))

Max Activating Token Index: 154

Text #14

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3045. Min Act: -0.0000

Data Index: 492004 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1108109 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3168. Min Act: -0.0000

Data Index: 478931 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1025416 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2812. Min Act: -0.0000

Data Index: 655034 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2889. Min Act: -0.0000

Data Index: 1057089 (C4 (Web Text))

Max Activating Token Index: 449