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

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

Neuron 3668 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: 0.9678. Min Range: -0.9678

Max Act: 0.8745. Min Act: -0.0002

Data Index: 317663 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.9678. Min Act: -0.0001

Data Index: 682996 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.7886. Min Act: -0.0001

Data Index: 1156922 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.7620. Min Act: -0.0002

Data Index: 1117374 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.7711. Min Act: -0.0001

Data Index: 651582 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.7808. Min Act: -0.0002

Data Index: 9561 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.8113. Min Act: -0.0002

Data Index: 120328 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.7812. Min Act: -0.0001

Data Index: 492035 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.7316. Min Act: -0.0002

Data Index: 387719 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.8336. Min Act: -0.0001

Data Index: 691437 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.7818. Min Act: -0.0002

Data Index: 690500 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.7995. Min Act: -0.0002

Data Index: 282070 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.8185. Min Act: -0.0002

Data Index: 1357383 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.8045. Min Act: -0.0001

Data Index: 1165709 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.8066. Min Act: -0.0002

Data Index: 54077 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.7857. Min Act: -0.0002

Data Index: 12283 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.7963. Min Act: -0.0001

Data Index: 30562 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.7267. Min Act: -0.0002

Data Index: 603928 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.7907. Min Act: -0.0001

Data Index: 1272832 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.9678. Min Range: -0.9678

Max Act: 0.7482. Min Act: -0.0002

Data Index: 1350541 (C4 (Web Text))

Max Activating Token Index: 228