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

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

Neuron 30 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: 1.1120. Min Range: -1.1120

Max Act: 1.1120. Min Act: -0.0000

Data Index: 341824 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.1120. Min Range: -1.1120

Max Act: 1.0981. Min Act: -0.0000

Data Index: 706161 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 1.1120. Min Range: -1.1120

Max Act: 1.1063. Min Act: -0.0000

Data Index: 628570 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 1.1120. Min Range: -1.1120

Max Act: 1.1064. Min Act: -0.0000

Data Index: 688268 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1014795 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.9860. Min Act: -0.0000

Data Index: 780046 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.8238. Min Act: -0.0000

Data Index: 940081 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.8436. Min Act: -0.0000

Data Index: 1343439 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7910. Min Act: -0.0000

Data Index: 557327 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.8000. Min Act: -0.0000

Data Index: 906847 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1190350 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.8212. Min Act: -0.0000

Data Index: 996587 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7580. Min Act: -0.0000

Data Index: 210648 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7223. Min Act: -0.0000

Data Index: 100978 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7400. Min Act: -0.0000

Data Index: 414835 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1298272 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7513. Min Act: -0.0000

Data Index: 1225453 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1121434 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7183. Min Act: -0.0000

Data Index: 353665 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 1.1120. Min Range: -1.1120

Max Act: 0.7011. Min Act: -0.0000

Data Index: 773540 (C4 (Web Text))

Max Activating Token Index: 128