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

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

Neuron 3849 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.6193. Min Act: -0.0000

Data Index: 79296 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.5167. Min Act: -0.0000

Data Index: 1041698 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.5120. Min Act: -0.0000

Data Index: 304897 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.4611. Min Act: -0.0000

Data Index: 1064828 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.3776. Min Act: -0.0000

Data Index: 332555 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.3258. Min Act: -0.0000

Data Index: 3783 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.2440. Min Act: -0.0000

Data Index: 1239779 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.1568. Min Act: -0.0000

Data Index: 541094 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.1748. Min Act: -0.0000

Data Index: 615094 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.0532. Min Act: -0.0000

Data Index: 57132 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.0052. Min Act: -0.0000

Data Index: 1107985 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.1242. Min Act: -0.0000

Data Index: 11041 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.1176. Min Act: -0.0000

Data Index: 238117 (C4 (Web Text))

Max Activating Token Index: 959

Text #13

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.0751. Min Act: -0.0000

Data Index: 253716 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.0235. Min Act: -0.0000

Data Index: 879623 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.0887. Min Act: -0.0000

Data Index: 824856 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.0171. Min Act: -0.0000

Data Index: 272264 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.0286. Min Act: -0.0000

Data Index: 873097 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.0280. Min Act: -0.0000

Data Index: 98545 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.6193. Min Range: -1.6193

Max Act: 1.0245. Min Act: -0.0000

Data Index: 714235 (C4 (Web Text))

Max Activating Token Index: 63