Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 484 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0883. Min Act: -0.0005

Data Index: 625754 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0908. Min Act: -0.0005

Data Index: 279860 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0899. Min Act: -0.0005

Data Index: 1335046 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0881. Min Act: -0.0005

Data Index: 439871 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0879. Min Act: -0.0005

Data Index: 984215 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0863. Min Act: -0.0005

Data Index: 435899 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0833. Min Act: -0.0005

Data Index: 240310 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0846. Min Act: -0.0005

Data Index: 865620 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0792. Min Act: -0.0005

Data Index: 388970 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0758. Min Act: -0.0005

Data Index: 1112489 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0796. Min Act: -0.0005

Data Index: 676823 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0808. Min Act: -0.0005

Data Index: 1353831 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0767. Min Act: -0.0005

Data Index: 912002 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0765. Min Act: -0.0005

Data Index: 389062 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0774. Min Act: -0.0005

Data Index: 1077241 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0743. Min Act: -0.0005

Data Index: 174346 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0754. Min Act: -0.0005

Data Index: 992362 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0729. Min Act: -0.0005

Data Index: 599125 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0762. Min Act: -0.0005

Data Index: 1072337 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0760. Min Act: -0.0005

Data Index: 249761 (C4 (Web Text))

Max Activating Token Index: 386