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

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

Neuron 5194 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8014. Min Range: -3.8014

Max Act: 3.8014. Min Act: -0.0000

Data Index: 813763 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 3.8014. Min Range: -3.8014

Max Act: 3.6819. Min Act: -0.0000

Data Index: 1237320 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 3.8014. Min Range: -3.8014

Max Act: 3.5044. Min Act: -0.0000

Data Index: 1193319 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 3.8014. Min Range: -3.8014

Max Act: 3.6156. Min Act: -0.0000

Data Index: 384701 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 3.8014. Min Range: -3.8014

Max Act: 3.2350. Min Act: -0.0000

Data Index: 997645 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 3.8014. Min Range: -3.8014

Max Act: 3.3408. Min Act: -0.0000

Data Index: 928555 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 3.8014. Min Range: -3.8014

Max Act: 3.3968. Min Act: -0.0000

Data Index: 1288829 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 3.8014. Min Range: -3.8014

Max Act: 2.8413. Min Act: -0.0000

Data Index: 183921 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 3.8014. Min Range: -3.8014

Max Act: 2.8320. Min Act: -0.0000

Data Index: 21158 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 3.8014. Min Range: -3.8014

Max Act: 2.9049. Min Act: -0.0000

Data Index: 976846 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 3.8014. Min Range: -3.8014

Max Act: 2.8912. Min Act: -0.0000

Data Index: 38733 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 3.8014. Min Range: -3.8014

Max Act: 2.8693. Min Act: -0.0000

Data Index: 626605 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 3.8014. Min Range: -3.8014

Max Act: 2.8352. Min Act: -0.0000

Data Index: 136293 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 3.8014. Min Range: -3.8014

Max Act: 2.6838. Min Act: -0.0000

Data Index: 565753 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 3.8014. Min Range: -3.8014

Max Act: 3.0832. Min Act: -0.0000

Data Index: 1165536 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 3.8014. Min Range: -3.8014

Max Act: 2.8859. Min Act: -0.0000

Data Index: 438120 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 3.8014. Min Range: -3.8014

Max Act: 2.7697. Min Act: -0.0000

Data Index: 680796 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 3.8014. Min Range: -3.8014

Max Act: 2.7310. Min Act: -0.0000

Data Index: 474156 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 3.8014. Min Range: -3.8014

Max Act: 2.4471. Min Act: -0.0000

Data Index: 1305481 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 3.8014. Min Range: -3.8014

Max Act: 2.5597. Min Act: -0.0000

Data Index: 706345 (C4 (Web Text))

Max Activating Token Index: 595