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

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

Neuron 1119 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.5604. Min Act: -0.0000

Data Index: 485175 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.7256. Min Act: -0.0000

Data Index: 1276320 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.2384. Min Act: -0.0000

Data Index: 861698 (C4 (Web Text))

Max Activating Token Index: 29

Text #3

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.4142. Min Act: -0.0001

Data Index: 1263381 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 3.7999. Min Range: -3.7999

Max Act: 2.7935. Min Act: -0.0001

Data Index: 485333 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.3253. Min Act: -0.0000

Data Index: 50719 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.7999. Min Act: -0.0000

Data Index: 278938 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.1431. Min Act: -0.0001

Data Index: 1129455 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.0581. Min Act: -0.0000

Data Index: 725869 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.1376. Min Act: -0.0000

Data Index: 257665 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 3.7999. Min Range: -3.7999

Max Act: 2.8140. Min Act: -0.0001

Data Index: 848848 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.0897. Min Act: -0.0000

Data Index: 107812 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.3754. Min Act: -0.0000

Data Index: 457052 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 3.7999. Min Range: -3.7999

Max Act: 2.6371. Min Act: -0.0000

Data Index: 860666 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.0732. Min Act: -0.0001

Data Index: 1135191 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.6599. Min Act: -0.0000

Data Index: 458452 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.0367. Min Act: -0.0000

Data Index: 152074 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 3.7999. Min Range: -3.7999

Max Act: 2.6379. Min Act: -0.0001

Data Index: 385120 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 3.7999. Min Range: -3.7999

Max Act: 3.3194. Min Act: -0.0000

Data Index: 442279 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 3.7999. Min Range: -3.7999

Max Act: 2.9971. Min Act: -0.0000

Data Index: 682504 (C4 (Web Text))

Max Activating Token Index: 777