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

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

Neuron 4048 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: 0.9543. Min Range: -0.9543

Max Act: 0.9543. Min Act: -0.0000

Data Index: 686352 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1274112 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7649. Min Act: -0.0000

Data Index: 731382 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1173383 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7368. Min Act: -0.0000

Data Index: 157572 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7408. Min Act: -0.0000

Data Index: 1233899 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1213185 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.6719. Min Act: -0.0000

Data Index: 114878 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.6240. Min Act: -0.0000

Data Index: 207068 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.6505. Min Act: -0.0000

Data Index: 685308 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.6188. Min Act: -0.0000

Data Index: 806469 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.6359. Min Act: 0.0000

Data Index: 265127 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1170077 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.5913. Min Act: -0.0000

Data Index: 126407 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1008936 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.5829. Min Act: -0.0000

Data Index: 212885 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.6205. Min Act: -0.0000

Data Index: 259985 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.6149. Min Act: -0.0000

Data Index: 524746 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.5970. Min Act: -0.0000

Data Index: 361300 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.9543. Min Range: -0.9543

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1146710 (C4 (Web Text))

Max Activating Token Index: 896