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

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

Neuron 581 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: 0.8754. Min Range: -0.8754

Max Act: 0.8754. Min Act: -0.0002

Data Index: 121669 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.8243. Min Act: -0.0002

Data Index: 1246464 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.8343. Min Act: -0.0002

Data Index: 571746 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.8049. Min Act: -0.0002

Data Index: 251897 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.8386. Min Act: -0.0001

Data Index: 1143571 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.8096. Min Act: -0.0002

Data Index: 983900 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7371. Min Act: -0.0002

Data Index: 1004107 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7399. Min Act: -0.0002

Data Index: 41953 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7514. Min Act: -0.0001

Data Index: 180852 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7220. Min Act: -0.0002

Data Index: 258179 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7023. Min Act: -0.0001

Data Index: 413483 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.8419. Min Act: -0.0002

Data Index: 293906 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7486. Min Act: -0.0002

Data Index: 923651 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.6481. Min Act: -0.0002

Data Index: 933522 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7440. Min Act: -0.0002

Data Index: 212438 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7325. Min Act: -0.0001

Data Index: 698675 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.6687. Min Act: -0.0002

Data Index: 847498 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7096. Min Act: -0.0001

Data Index: 942591 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7010. Min Act: -0.0001

Data Index: 1291225 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7168. Min Act: -0.0002

Data Index: 971862 (C4 (Web Text))

Max Activating Token Index: 106