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

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

Neuron 730 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: 0.9256. Min Range: -0.9256

Max Act: 0.8715. Min Act: -0.0002

Data Index: 461240 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8325. Min Act: -0.0001

Data Index: 1011721 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8082. Min Act: -0.0002

Data Index: 367168 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8981. Min Act: -0.0002

Data Index: 145091 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.9256. Min Act: -0.0002

Data Index: 610518 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7795. Min Act: -0.0002

Data Index: 367936 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8765. Min Act: -0.0002

Data Index: 977096 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8250. Min Act: -0.0002

Data Index: 1287202 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7858. Min Act: -0.0001

Data Index: 198690 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7834. Min Act: -0.0002

Data Index: 886715 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7868. Min Act: -0.0001

Data Index: 550307 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8145. Min Act: -0.0001

Data Index: 1150474 (C4 (Web Text))

Max Activating Token Index: 112

Text #12

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.8019. Min Act: -0.0002

Data Index: 929677 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7198. Min Act: -0.0002

Data Index: 113483 (C4 (Web Text))

Max Activating Token Index: 472

Text #14

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7890. Min Act: -0.0001

Data Index: 347066 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7386. Min Act: -0.0001

Data Index: 647371 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7752. Min Act: -0.0002

Data Index: 77629 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7630. Min Act: -0.0001

Data Index: 12562 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.7449. Min Act: -0.0002

Data Index: 971699 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.9256. Min Range: -0.9256

Max Act: 0.6818. Min Act: -0.0002

Data Index: 450418 (C4 (Web Text))

Max Activating Token Index: 573