Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1451 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.5250. Min Act: -0.0001

Data Index: 915369 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.3300. Min Act: -0.0001

Data Index: 618314 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.3246. Min Act: -0.0001

Data Index: 644369 (C4 (Web Text))

Max Activating Token Index: 758

Text #3

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.3153. Min Act: -0.0001

Data Index: 705799 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.3125. Min Act: -0.0001

Data Index: 1169588 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.2929. Min Act: -0.0001

Data Index: 218254 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.2893. Min Act: -0.0001

Data Index: 513757 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.2798. Min Act: -0.0001

Data Index: 371089 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.2706. Min Act: -0.0001

Data Index: 735055 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.2924. Min Act: -0.0001

Data Index: 482497 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.2768. Min Act: -0.0001

Data Index: 542360 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.2593. Min Act: -0.0001

Data Index: 1056172 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.2733. Min Act: -0.0001

Data Index: 248030 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.2825. Min Act: -0.0001

Data Index: 490840 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.3225. Min Act: -0.0001

Data Index: 307583 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.2691. Min Act: -0.0001

Data Index: 1123514 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.2587. Min Act: -0.0001

Data Index: 896212 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.2271. Min Act: -0.0001

Data Index: 241464 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.2585. Min Act: -0.0001

Data Index: 145547 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.5250. Min Range: -0.5250

Max Act: 0.2395. Min Act: -0.0001

Data Index: 280370 (C4 (Web Text))

Max Activating Token Index: 711