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

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

Neuron 73 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: 0.6629. Min Range: -0.6629

Max Act: 0.5714. Min Act: -0.0001

Data Index: 598302 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5717. Min Act: -0.0001

Data Index: 335764 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6629. Min Act: -0.0001

Data Index: 475822 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6160. Min Act: -0.0001

Data Index: 1158017 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5540. Min Act: -0.0001

Data Index: 721898 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6049. Min Act: -0.0001

Data Index: 924403 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5335. Min Act: -0.0001

Data Index: 657848 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5442. Min Act: -0.0001

Data Index: 1311379 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5640. Min Act: -0.0001

Data Index: 824666 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5462. Min Act: -0.0001

Data Index: 596198 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5629. Min Act: -0.0000

Data Index: 1508449 (Python Code)

Max Activating Token Index: 170

Text #11

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5836. Min Act: -0.0001

Data Index: 650779 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5265. Min Act: -0.0001

Data Index: 28910 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1421500 (Python Code)

Max Activating Token Index: 130

Text #14

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5161. Min Act: -0.0001

Data Index: 295416 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1392670 (Python Code)

Max Activating Token Index: 27

Text #16

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5518. Min Act: -0.0001

Data Index: 79217 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5141. Min Act: -0.0001

Data Index: 1405794 (Python Code)

Max Activating Token Index: 949

Text #18

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5502. Min Act: -0.0001

Data Index: 754238 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5468. Min Act: -0.0001

Data Index: 1035006 (C4 (Web Text))

Max Activating Token Index: 962