Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3158 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1357. Min Range: -1.1357

Max Act: 1.1237. Min Act: -0.0001

Data Index: 495789 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 1.1357. Min Range: -1.1357

Max Act: 1.0999. Min Act: -0.0001

Data Index: 700506 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 1.1357. Min Range: -1.1357

Max Act: 1.1357. Min Act: -0.0001

Data Index: 499916 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 1.1357. Min Range: -1.1357

Max Act: 1.0157. Min Act: -0.0001

Data Index: 1216657 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.9964. Min Act: -0.0001

Data Index: 160167 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.9177. Min Act: -0.0001

Data Index: 995859 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.9261. Min Act: -0.0001

Data Index: 1171476 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.9189. Min Act: -0.0001

Data Index: 426432 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.8580. Min Act: -0.0001

Data Index: 188244 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.8519. Min Act: -0.0001

Data Index: 1302877 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.9041. Min Act: -0.0001

Data Index: 310621 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.8720. Min Act: -0.0001

Data Index: 571895 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.8826. Min Act: -0.0001

Data Index: 403649 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.8561. Min Act: -0.0001

Data Index: 276703 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.8728. Min Act: -0.0001

Data Index: 566118 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.8186. Min Act: -0.0001

Data Index: 415493 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.8699. Min Act: -0.0001

Data Index: 99809 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.8810. Min Act: -0.0001

Data Index: 116009 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.8553. Min Act: -0.0001

Data Index: 1324913 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 1.1357. Min Range: -1.1357

Max Act: 0.8068. Min Act: -0.0001

Data Index: 212025 (C4 (Web Text))

Max Activating Token Index: 196