Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2677 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0037. Min Act: -0.0003

Data Index: 217875 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0036. Min Act: -0.0003

Data Index: 9046 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0036. Min Act: -0.0003

Data Index: 52565 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1300458 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0035. Min Act: -0.0003

Data Index: 958906 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0035. Min Act: -0.0003

Data Index: 354296 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 531099 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 710049 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 220695 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 1102558 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 727682 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 812237 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 799131 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 403800 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 1243845 (C4 (Web Text))

Max Activating Token Index: 646

Text #15

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 258569 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0033. Min Act: -0.0003

Data Index: 335040 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0034. Min Act: -0.0003

Data Index: 1225926 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0033. Min Act: -0.0003

Data Index: 268257 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.0037. Min Range: -0.0037

Max Act: 0.0033. Min Act: -0.0003

Data Index: 87527 (C4 (Web Text))

Max Activating Token Index: 168