Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5795 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4250. Min Range: -3.4250

Max Act: 3.4250. Min Act: -0.0000

Data Index: 11877 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 3.4250. Min Range: -3.4250

Max Act: 2.8928. Min Act: -0.0000

Data Index: 1090692 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 3.4250. Min Range: -3.4250

Max Act: 2.5194. Min Act: -0.0000

Data Index: 73602 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 3.4250. Min Range: -3.4250

Max Act: 2.2838. Min Act: -0.0000

Data Index: 706382 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 3.4250. Min Range: -3.4250

Max Act: 2.0103. Min Act: -0.0000

Data Index: 855373 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 3.4250. Min Range: -3.4250

Max Act: 1.7752. Min Act: -0.0000

Data Index: 233181 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 3.4250. Min Range: -3.4250

Max Act: 1.6209. Min Act: -0.0000

Data Index: 462353 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 3.4250. Min Range: -3.4250

Max Act: 1.2862. Min Act: 0.0000

Data Index: 339835 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 3.4250. Min Range: -3.4250

Max Act: 1.4415. Min Act: -0.0000

Data Index: 685625 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 3.4250. Min Range: -3.4250

Max Act: 1.1295. Min Act: -0.0000

Data Index: 826747 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 3.4250. Min Range: -3.4250

Max Act: 1.2762. Min Act: -0.0000

Data Index: 165416 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 3.4250. Min Range: -3.4250

Max Act: 1.1777. Min Act: -0.0000

Data Index: 831732 (C4 (Web Text))

Max Activating Token Index: 153

Text #12

Max Range: 3.4250. Min Range: -3.4250

Max Act: 1.2546. Min Act: 0.0000

Data Index: 238064 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 3.4250. Min Range: -3.4250

Max Act: 1.2481. Min Act: 0.0000

Data Index: 371992 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 3.4250. Min Range: -3.4250

Max Act: 1.2478. Min Act: -0.0000

Data Index: 1146688 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 3.4250. Min Range: -3.4250

Max Act: 1.2384. Min Act: -0.0000

Data Index: 177365 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 3.4250. Min Range: -3.4250

Max Act: 1.3097. Min Act: 0.0000

Data Index: 890099 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 3.4250. Min Range: -3.4250

Max Act: 1.1480. Min Act: 0.0000

Data Index: 681468 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 3.4250. Min Range: -3.4250

Max Act: 1.1512. Min Act: -0.0000

Data Index: 680959 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 3.4250. Min Range: -3.4250

Max Act: 1.2215. Min Act: -0.0000

Data Index: 255064 (C4 (Web Text))

Max Activating Token Index: 217