Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1840 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.7766. Min Act: -0.0001

Data Index: 193990 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.6362. Min Act: -0.0001

Data Index: 64338 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.8673. Min Act: -0.0001

Data Index: 436598 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.7359. Min Act: -0.0001

Data Index: 18824 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.7555. Min Act: -0.0001

Data Index: 844481 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.6783. Min Act: -0.0001

Data Index: 65425 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.5441. Min Act: -0.0001

Data Index: 1217481 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.5608. Min Act: -0.0001

Data Index: 206503 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.6406. Min Act: -0.0001

Data Index: 417014 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.6014. Min Act: -0.0001

Data Index: 780862 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.4628. Min Act: -0.0001

Data Index: 311603 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.5756. Min Act: -0.0001

Data Index: 1191457 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.6125. Min Act: -0.0001

Data Index: 875418 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.6004. Min Act: -0.0001

Data Index: 669715 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.6328. Min Act: -0.0001

Data Index: 595004 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.5103. Min Act: -0.0001

Data Index: 130481 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.4186. Min Act: -0.0001

Data Index: 886227 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.6350. Min Act: -0.0001

Data Index: 376179 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.4729. Min Act: -0.0001

Data Index: 696952 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 1.8673. Min Range: -1.8673

Max Act: 1.5086. Min Act: -0.0001

Data Index: 997829 (C4 (Web Text))

Max Activating Token Index: 452