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

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

Neuron 1733 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.9917. Min Act: -0.0003

Data Index: 1178740 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.7620. Min Act: -0.0003

Data Index: 227273 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.6965. Min Act: -0.0003

Data Index: 981541 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.4068. Min Act: -0.0003

Data Index: 375806 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.3475. Min Act: -0.0003

Data Index: 1122778 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.3683. Min Act: -0.0003

Data Index: 228786 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.3251. Min Act: -0.0002

Data Index: 252564 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.2928. Min Act: -0.0003

Data Index: 890527 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.2738. Min Act: -0.0003

Data Index: 1106872 (C4 (Web Text))

Max Activating Token Index: 878

Text #9

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.2752. Min Act: -0.0003

Data Index: 217005 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.2371. Min Act: -0.0003

Data Index: 308740 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.2001. Min Act: -0.0003

Data Index: 296354 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.2162. Min Act: -0.0003

Data Index: 26582 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.2254. Min Act: -0.0003

Data Index: 435432 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.2146. Min Act: -0.0003

Data Index: 819224 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.2837. Min Act: -0.0002

Data Index: 592361 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.1896. Min Act: -0.0003

Data Index: 1145071 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.2333. Min Act: -0.0003

Data Index: 931887 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.1977. Min Act: -0.0003

Data Index: 604954 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 1.9917. Min Range: -1.9917

Max Act: 1.2077. Min Act: -0.0003

Data Index: 786574 (C4 (Web Text))

Max Activating Token Index: 632