Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4694 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0098. Min Range: -3.0098

Max Act: 3.0098. Min Act: -0.0000

Data Index: 33502 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 3.0098. Min Range: -3.0098

Max Act: 2.3946. Min Act: -0.0000

Data Index: 1211308 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 3.0098. Min Range: -3.0098

Max Act: 2.3973. Min Act: -0.0000

Data Index: 1328449 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 3.0098. Min Range: -3.0098

Max Act: 2.2715. Min Act: -0.0000

Data Index: 467137 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 3.0098. Min Range: -3.0098

Max Act: 2.3058. Min Act: -0.0000

Data Index: 607251 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 3.0098. Min Range: -3.0098

Max Act: 2.1814. Min Act: -0.0000

Data Index: 702472 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 3.0098. Min Range: -3.0098

Max Act: 2.2636. Min Act: -0.0000

Data Index: 461162 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 3.0098. Min Range: -3.0098

Max Act: 1.9818. Min Act: -0.0000

Data Index: 433529 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 3.0098. Min Range: -3.0098

Max Act: 2.0546. Min Act: -0.0000

Data Index: 1323471 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 3.0098. Min Range: -3.0098

Max Act: 2.0253. Min Act: -0.0000

Data Index: 1221079 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 3.0098. Min Range: -3.0098

Max Act: 1.9609. Min Act: -0.0000

Data Index: 715241 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 3.0098. Min Range: -3.0098

Max Act: 2.0372. Min Act: -0.0000

Data Index: 1198564 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 3.0098. Min Range: -3.0098

Max Act: 2.0488. Min Act: -0.0000

Data Index: 1001179 (C4 (Web Text))

Max Activating Token Index: 409

Text #13

Max Range: 3.0098. Min Range: -3.0098

Max Act: 1.9135. Min Act: -0.0000

Data Index: 662884 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 3.0098. Min Range: -3.0098

Max Act: 1.9933. Min Act: -0.0000

Data Index: 236120 (C4 (Web Text))

Max Activating Token Index: 311

Text #15

Max Range: 3.0098. Min Range: -3.0098

Max Act: 1.9945. Min Act: -0.0000

Data Index: 789967 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 3.0098. Min Range: -3.0098

Max Act: 1.9864. Min Act: -0.0000

Data Index: 295022 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 3.0098. Min Range: -3.0098

Max Act: 2.2054. Min Act: -0.0000

Data Index: 1122919 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 3.0098. Min Range: -3.0098

Max Act: 2.0940. Min Act: -0.0000

Data Index: 596556 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 3.0098. Min Range: -3.0098

Max Act: 1.9559. Min Act: -0.0000

Data Index: 897452 (C4 (Web Text))

Max Activating Token Index: 685