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

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

Neuron 2512 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0359. Min Act: -0.0004

Data Index: 1255983 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0331. Min Act: -0.0004

Data Index: 145943 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0324. Min Act: -0.0004

Data Index: 1071617 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0320. Min Act: -0.0004

Data Index: 1097335 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0360. Min Act: -0.0004

Data Index: 501386 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0315. Min Act: -0.0004

Data Index: 1166296 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0314. Min Act: -0.0004

Data Index: 189712 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0318. Min Act: -0.0004

Data Index: 270807 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0294. Min Act: -0.0004

Data Index: 691743 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0292. Min Act: -0.0004

Data Index: 158046 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0323. Min Act: -0.0004

Data Index: 598785 (C4 (Web Text))

Max Activating Token Index: 578

Text #11

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0300. Min Act: -0.0004

Data Index: 1114951 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0282. Min Act: -0.0004

Data Index: 332671 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0291. Min Act: -0.0004

Data Index: 1093186 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0288. Min Act: -0.0004

Data Index: 294421 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0277. Min Act: -0.0004

Data Index: 124265 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0282. Min Act: -0.0004

Data Index: 964615 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0287. Min Act: -0.0004

Data Index: 579624 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0268. Min Act: -0.0004

Data Index: 108658 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0285. Min Act: -0.0004

Data Index: 1210613 (C4 (Web Text))

Max Activating Token Index: 18