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

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

Neuron 6137 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3267. Min Range: -2.3267

Max Act: 2.2419. Min Act: -0.0000

Data Index: 46651 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 2.3267. Min Range: -2.3267

Max Act: 2.3267. Min Act: -0.0000

Data Index: 171633 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 2.3267. Min Range: -2.3267

Max Act: 2.2894. Min Act: -0.0000

Data Index: 1143234 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.8839. Min Act: -0.0000

Data Index: 1131566 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.8522. Min Act: -0.0000

Data Index: 68400 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.9034. Min Act: -0.0000

Data Index: 413462 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 2.3267. Min Range: -2.3267

Max Act: 2.0106. Min Act: -0.0000

Data Index: 110623 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.8536. Min Act: -0.0000

Data Index: 912500 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.8449. Min Act: -0.0000

Data Index: 400142 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.7345. Min Act: -0.0000

Data Index: 282117 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.6884. Min Act: -0.0000

Data Index: 131973 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.7001. Min Act: -0.0000

Data Index: 721282 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.7583. Min Act: -0.0000

Data Index: 168850 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.6117. Min Act: -0.0000

Data Index: 243510 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.7805. Min Act: -0.0000

Data Index: 771929 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.6729. Min Act: -0.0000

Data Index: 1251709 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.6740. Min Act: -0.0000

Data Index: 858475 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.5590. Min Act: -0.0000

Data Index: 1048871 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.6536. Min Act: -0.0000

Data Index: 697122 (C4 (Web Text))

Max Activating Token Index: 831

Text #19

Max Range: 2.3267. Min Range: -2.3267

Max Act: 1.6234. Min Act: -0.0000

Data Index: 961052 (C4 (Web Text))

Max Activating Token Index: 895