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

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

Neuron 1813 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7598. Min Act: -0.0000

Data Index: 115885 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.8252. Min Act: -0.0000

Data Index: 519287 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7872. Min Act: -0.0000

Data Index: 661703 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7524. Min Act: -0.0000

Data Index: 125582 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7542. Min Act: -0.0000

Data Index: 299577 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7425. Min Act: -0.0000

Data Index: 290711 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1320239 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7261. Min Act: -0.0000

Data Index: 527694 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1215816 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7184. Min Act: -0.0000

Data Index: 685693 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1214638 (C4 (Web Text))

Max Activating Token Index: 1016

Text #11

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6569. Min Act: -0.0000

Data Index: 297472 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6728. Min Act: -0.0000

Data Index: 608936 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6278. Min Act: 0.0003

Data Index: 234722 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6412. Min Act: -0.0000

Data Index: 464542 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6347. Min Act: -0.0000

Data Index: 918819 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6272. Min Act: -0.0000

Data Index: 21611 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6377. Min Act: -0.0000

Data Index: 169059 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6123. Min Act: -0.0000

Data Index: 209924 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.8252. Min Range: -0.8252

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1102969 (C4 (Web Text))

Max Activating Token Index: 424