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

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

Neuron 2356 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.5014. Min Act: -0.0000

Data Index: 919579 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.4487. Min Act: -0.0001

Data Index: 1512132 (Python Code)

Max Activating Token Index: 864

Text #2

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.4145. Min Act: -0.0001

Data Index: 1448836 (Python Code)

Max Activating Token Index: 689

Text #3

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.4134. Min Act: -0.0001

Data Index: 1572941 (Python Code)

Max Activating Token Index: 620

Text #4

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3512. Min Act: -0.0001

Data Index: 871747 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3426. Min Act: -0.0000

Data Index: 564001 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3228. Min Act: -0.0001

Data Index: 517698 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3154. Min Act: -0.0001

Data Index: 192381 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3315. Min Act: -0.0001

Data Index: 128212 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3090. Min Act: -0.0001

Data Index: 906196 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.2867. Min Act: -0.0001

Data Index: 952516 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3128. Min Act: -0.0000

Data Index: 558328 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1354944 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.2894. Min Act: -0.0000

Data Index: 1345105 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.2896. Min Act: -0.0001

Data Index: 983144 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.2705. Min Act: -0.0001

Data Index: 271233 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.2863. Min Act: -0.0001

Data Index: 771986 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.2883. Min Act: -0.0001

Data Index: 279319 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.2563. Min Act: -0.0001

Data Index: 817667 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.5014. Min Range: -0.5014

Max Act: 0.2911. Min Act: -0.0000

Data Index: 182510 (C4 (Web Text))

Max Activating Token Index: 147