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

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

Neuron 2490 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3759. Min Act: -0.0000

Data Index: 405256 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1023292 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3687. Min Act: -0.0000

Data Index: 211166 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3362. Min Act: -0.0000

Data Index: 880582 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3180. Min Act: -0.0000

Data Index: 238145 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3303. Min Act: -0.0000

Data Index: 1121042 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1130112 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3399. Min Act: -0.0000

Data Index: 1174551 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3169. Min Act: -0.0000

Data Index: 982127 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3087. Min Act: -0.0000

Data Index: 631296 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3043. Min Act: -0.0000

Data Index: 157016 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2938. Min Act: -0.0000

Data Index: 235675 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3004. Min Act: -0.0000

Data Index: 609277 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3015. Min Act: -0.0000

Data Index: 816930 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2573. Min Act: -0.0000

Data Index: 1075305 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1079531 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.3107. Min Act: -0.0000

Data Index: 72944 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2991. Min Act: -0.0000

Data Index: 961653 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2962. Min Act: -0.0000

Data Index: 593245 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.3759. Min Range: -0.3759

Max Act: 0.2748. Min Act: -0.0000

Data Index: 658069 (C4 (Web Text))

Max Activating Token Index: 365