Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3300 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2477. Min Range: -1.2477

Max Act: 1.2162. Min Act: -0.0002

Data Index: 912933 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 1.2477. Min Range: -1.2477

Max Act: 1.2477. Min Act: -0.0002

Data Index: 564942 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 1.2477. Min Range: -1.2477

Max Act: 1.1891. Min Act: -0.0001

Data Index: 509649 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 1.2477. Min Range: -1.2477

Max Act: 1.0568. Min Act: -0.0002

Data Index: 1318830 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 1.2477. Min Range: -1.2477

Max Act: 1.0900. Min Act: -0.0001

Data Index: 1312474 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 1.2477. Min Range: -1.2477

Max Act: 1.0603. Min Act: -0.0001

Data Index: 730948 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 1.2477. Min Range: -1.2477

Max Act: 1.1148. Min Act: -0.0002

Data Index: 546863 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 1.2477. Min Range: -1.2477

Max Act: 1.1302. Min Act: -0.0002

Data Index: 388983 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 1.2477. Min Range: -1.2477

Max Act: 1.0639. Min Act: -0.0002

Data Index: 405504 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 1.2477. Min Range: -1.2477

Max Act: 1.2003. Min Act: -0.0002

Data Index: 295992 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 1.2477. Min Range: -1.2477

Max Act: 0.9541. Min Act: -0.0001

Data Index: 1387945 (Python Code)

Max Activating Token Index: 781

Text #11

Max Range: 1.2477. Min Range: -1.2477

Max Act: 0.9956. Min Act: -0.0002

Data Index: 378970 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 1.2477. Min Range: -1.2477

Max Act: 0.9199. Min Act: -0.0001

Data Index: 63299 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 1.2477. Min Range: -1.2477

Max Act: 1.1539. Min Act: -0.0001

Data Index: 152141 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 1.2477. Min Range: -1.2477

Max Act: 0.9805. Min Act: -0.0001

Data Index: 848867 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 1.2477. Min Range: -1.2477

Max Act: 0.9133. Min Act: -0.0002

Data Index: 1141208 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 1.2477. Min Range: -1.2477

Max Act: 1.0338. Min Act: -0.0001

Data Index: 229116 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 1.2477. Min Range: -1.2477

Max Act: 0.9665. Min Act: -0.0002

Data Index: 117823 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 1.2477. Min Range: -1.2477

Max Act: 0.9422. Min Act: -0.0002

Data Index: 886981 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 1.2477. Min Range: -1.2477

Max Act: 0.9628. Min Act: -0.0001

Data Index: 799596 (C4 (Web Text))

Max Activating Token Index: 421