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

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

Neuron 4965 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.9452. Min Act: -0.0000

Data Index: 743144 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7901. Min Act: -0.0000

Data Index: 520004 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1314931 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7918. Min Act: -0.0000

Data Index: 1005096 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6818. Min Act: -0.0000

Data Index: 822762 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6384. Min Act: -0.0000

Data Index: 1125458 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6823. Min Act: -0.0000

Data Index: 729640 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.7101. Min Act: -0.0000

Data Index: 340541 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6145. Min Act: -0.0000

Data Index: 235399 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6419. Min Act: -0.0000

Data Index: 311801 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6558. Min Act: -0.0000

Data Index: 1050862 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6274. Min Act: -0.0000

Data Index: 8441 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6882. Min Act: -0.0000

Data Index: 193740 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.6481. Min Act: -0.0000

Data Index: 583208 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1286554 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.5984. Min Act: -0.0000

Data Index: 908855 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.5841. Min Act: -0.0000

Data Index: 132635 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.5784. Min Act: -0.0000

Data Index: 769057 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.5712. Min Act: -0.0000

Data Index: 154047 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.9452. Min Range: -0.9452

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1357537 (C4 (Web Text))

Max Activating Token Index: 453