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

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

Neuron 370 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7802. Min Act: -0.0003

Data Index: 551922 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.8178. Min Act: -0.0003

Data Index: 279090 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6713. Min Act: -0.0003

Data Index: 812671 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7613. Min Act: -0.0003

Data Index: 103923 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7386. Min Act: -0.0003

Data Index: 168858 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7146. Min Act: -0.0004

Data Index: 1345879 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6925. Min Act: -0.0003

Data Index: 732415 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7435. Min Act: -0.0003

Data Index: 1021718 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6798. Min Act: -0.0003

Data Index: 1105297 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6179. Min Act: -0.0003

Data Index: 1120986 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6758. Min Act: -0.0003

Data Index: 1106487 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6876. Min Act: -0.0003

Data Index: 969525 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7302. Min Act: -0.0003

Data Index: 333728 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6979. Min Act: -0.0003

Data Index: 455853 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6611. Min Act: -0.0003

Data Index: 694858 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7496. Min Act: -0.0003

Data Index: 448454 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6836. Min Act: -0.0003

Data Index: 30798 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6239. Min Act: -0.0003

Data Index: 471427 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6740. Min Act: -0.0003

Data Index: 666006 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7416. Min Act: -0.0004

Data Index: 504314 (C4 (Web Text))

Max Activating Token Index: 383