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

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

Neuron 1487 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3210. Min Range: -1.3210

Max Act: 1.3210. Min Act: -0.0000

Data Index: 106665 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 1.3210. Min Range: -1.3210

Max Act: 1.2416. Min Act: -0.0000

Data Index: 494433 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 1.3210. Min Range: -1.3210

Max Act: 1.1828. Min Act: -0.0000

Data Index: 1286603 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 1.3210. Min Range: -1.3210

Max Act: 1.0807. Min Act: -0.0000

Data Index: 674200 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 1.3210. Min Range: -1.3210

Max Act: 1.0913. Min Act: -0.0000

Data Index: 122896 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 1.3210. Min Range: -1.3210

Max Act: 1.0667. Min Act: -0.0000

Data Index: 1231850 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 1.3210. Min Range: -1.3210

Max Act: 1.0836. Min Act: -0.0000

Data Index: 904961 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 1.3210. Min Range: -1.3210

Max Act: 1.1152. Min Act: -0.0000

Data Index: 1008310 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 1.3210. Min Range: -1.3210

Max Act: 1.1219. Min Act: -0.0000

Data Index: 307243 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 1.3210. Min Range: -1.3210

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1114599 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 1.3210. Min Range: -1.3210

Max Act: 1.0434. Min Act: 0.0000

Data Index: 50982 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 1.3210. Min Range: -1.3210

Max Act: 1.0717. Min Act: -0.0000

Data Index: 553746 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 1.3210. Min Range: -1.3210

Max Act: 0.9829. Min Act: -0.0000

Data Index: 299240 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 1.3210. Min Range: -1.3210

Max Act: 0.9883. Min Act: -0.0000

Data Index: 445409 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 1.3210. Min Range: -1.3210

Max Act: 0.9145. Min Act: 0.0000

Data Index: 130196 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 1.3210. Min Range: -1.3210

Max Act: 0.9778. Min Act: -0.0000

Data Index: 13718 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 1.3210. Min Range: -1.3210

Max Act: 0.9967. Min Act: -0.0000

Data Index: 559369 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 1.3210. Min Range: -1.3210

Max Act: 0.9488. Min Act: -0.0000

Data Index: 213421 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 1.3210. Min Range: -1.3210

Max Act: 0.9398. Min Act: -0.0000

Data Index: 1151218 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 1.3210. Min Range: -1.3210

Max Act: 0.9531. Min Act: -0.0000

Data Index: 269285 (C4 (Web Text))

Max Activating Token Index: 493