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

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

Neuron 3047 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: 1.6983. Min Range: -1.6983

Max Act: 1.6983. Min Act: -0.0000

Data Index: 1169198 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 1.6983. Min Range: -1.6983

Max Act: 1.6672. Min Act: -0.0000

Data Index: 216899 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 1.6983. Min Range: -1.6983

Max Act: 1.6384. Min Act: -0.0000

Data Index: 189960 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 1.6983. Min Range: -1.6983

Max Act: 1.5797. Min Act: -0.0000

Data Index: 750369 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 1.6983. Min Range: -1.6983

Max Act: 1.2661. Min Act: -0.0000

Data Index: 27050 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 1.6983. Min Range: -1.6983

Max Act: 1.3302. Min Act: -0.0000

Data Index: 980224 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 1.6983. Min Range: -1.6983

Max Act: 1.3039. Min Act: -0.0000

Data Index: 300223 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.6983. Min Range: -1.6983

Max Act: 1.1198. Min Act: -0.0000

Data Index: 348474 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 1.6983. Min Range: -1.6983

Max Act: 1.0395. Min Act: -0.0000

Data Index: 284108 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 1.6983. Min Range: -1.6983

Max Act: 0.8234. Min Act: -0.0000

Data Index: 556972 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 1.6983. Min Range: -1.6983

Max Act: 0.7973. Min Act: -0.0000

Data Index: 486823 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 1.6983. Min Range: -1.6983

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1238264 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 1.6983. Min Range: -1.6983

Max Act: 0.7124. Min Act: -0.0000

Data Index: 116860 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 1.6983. Min Range: -1.6983

Max Act: 0.6207. Min Act: -0.0000

Data Index: 720720 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 1.6983. Min Range: -1.6983

Max Act: 0.4756. Min Act: -0.0000

Data Index: 29137 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 1.6983. Min Range: -1.6983

Max Act: 0.5896. Min Act: -0.0000

Data Index: 480219 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 1.6983. Min Range: -1.6983

Max Act: 0.5576. Min Act: -0.0000

Data Index: 694001 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 1.6983. Min Range: -1.6983

Max Act: 0.4822. Min Act: -0.0000

Data Index: 199093 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 1.6983. Min Range: -1.6983

Max Act: 0.5260. Min Act: -0.0000

Data Index: 854216 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 1.6983. Min Range: -1.6983

Max Act: 0.5634. Min Act: -0.0000

Data Index: 333799 (C4 (Web Text))

Max Activating Token Index: 407