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

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

Neuron 839 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.5994. Min Act: -0.0000

Data Index: 1123318 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.1722. Min Act: -0.0000

Data Index: 154304 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.2720. Min Act: -0.0000

Data Index: 588571 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.1100. Min Act: -0.0000

Data Index: 633978 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.1012. Min Act: -0.0000

Data Index: 812008 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 1.5994. Min Range: -1.5994

Max Act: 1.0945. Min Act: -0.0000

Data Index: 484650 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 1.5994. Min Range: -1.5994

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1190242 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 1.5994. Min Range: -1.5994

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1316574 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 1.5994. Min Range: -1.5994

Max Act: 0.8082. Min Act: -0.0000

Data Index: 31725 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 1.5994. Min Range: -1.5994

Max Act: 0.7898. Min Act: -0.0000

Data Index: 202648 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.5994. Min Range: -1.5994

Max Act: 0.7580. Min Act: -0.0000

Data Index: 287045 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 1.5994. Min Range: -1.5994

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1084509 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 1.5994. Min Range: -1.5994

Max Act: 0.7470. Min Act: -0.0000

Data Index: 733344 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 1.5994. Min Range: -1.5994

Max Act: 0.6190. Min Act: -0.0000

Data Index: 1051923 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 1.5994. Min Range: -1.5994

Max Act: 0.7273. Min Act: 0.0000

Data Index: 388495 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 1.5994. Min Range: -1.5994

Max Act: 0.6767. Min Act: -0.0000

Data Index: 237954 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 1.5994. Min Range: -1.5994

Max Act: 0.6568. Min Act: -0.0000

Data Index: 1122264 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 1.5994. Min Range: -1.5994

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1215021 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 1.5994. Min Range: -1.5994

Max Act: 0.6059. Min Act: -0.0000

Data Index: 747592 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 1.5994. Min Range: -1.5994

Max Act: 0.5926. Min Act: -0.0000

Data Index: 712695 (C4 (Web Text))

Max Activating Token Index: 921