Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4096 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7744. Min Act: -0.0000

Data Index: 803478 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7088. Min Act: -0.0000

Data Index: 945676 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.7327. Min Act: -0.0000

Data Index: 223684 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6840. Min Act: -0.0000

Data Index: 133063 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6722. Min Act: -0.0000

Data Index: 283058 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6147. Min Act: -0.0000

Data Index: 661052 (C4 (Web Text))

Max Activating Token Index: 875

Text #6

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6929. Min Act: -0.0000

Data Index: 670692 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.6769. Min Act: -0.0000

Data Index: 345144 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.5043. Min Act: -0.0000

Data Index: 1296612 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.4448. Min Act: -0.0000

Data Index: 188706 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.3867. Min Act: -0.0000

Data Index: 427494 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.3649. Min Act: -0.0000

Data Index: 297853 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.3879. Min Act: -0.0000

Data Index: 433318 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1094379 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.3653. Min Act: -0.0000

Data Index: 176568 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.3376. Min Act: -0.0000

Data Index: 514125 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.3576. Min Act: -0.0000

Data Index: 767177 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.3479. Min Act: -0.0000

Data Index: 680400 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.3428. Min Act: -0.0000

Data Index: 768825 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.7744. Min Range: -0.7744

Max Act: 0.3113. Min Act: -0.0000

Data Index: 474241 (C4 (Web Text))

Max Activating Token Index: 30