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

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

Neuron 4172 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3002. Min Range: -2.3002

Max Act: 2.3002. Min Act: -0.0000

Data Index: 1063574 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 2.3002. Min Range: -2.3002

Max Act: 2.1782. Min Act: -0.0000

Data Index: 869600 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 2.3002. Min Range: -2.3002

Max Act: 2.2820. Min Act: -0.0000

Data Index: 657237 (C4 (Web Text))

Max Activating Token Index: 723

Text #3

Max Range: 2.3002. Min Range: -2.3002

Max Act: 1.9425. Min Act: -0.0000

Data Index: 428114 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 2.3002. Min Range: -2.3002

Max Act: 2.1679. Min Act: -0.0000

Data Index: 1029459 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 2.3002. Min Range: -2.3002

Max Act: 2.0526. Min Act: -0.0000

Data Index: 767290 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 2.3002. Min Range: -2.3002

Max Act: 1.9505. Min Act: -0.0000

Data Index: 1165888 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 2.3002. Min Range: -2.3002

Max Act: 1.8184. Min Act: -0.0000

Data Index: 518304 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 2.3002. Min Range: -2.3002

Max Act: 1.8255. Min Act: -0.0000

Data Index: 13133 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 2.3002. Min Range: -2.3002

Max Act: 1.7864. Min Act: -0.0000

Data Index: 1350397 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 2.3002. Min Range: -2.3002

Max Act: 1.8610. Min Act: -0.0000

Data Index: 253106 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 2.3002. Min Range: -2.3002

Max Act: 1.7671. Min Act: -0.0000

Data Index: 1138352 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 2.3002. Min Range: -2.3002

Max Act: 1.7508. Min Act: -0.0000

Data Index: 1042411 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 2.3002. Min Range: -2.3002

Max Act: 1.8468. Min Act: -0.0000

Data Index: 96665 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 2.3002. Min Range: -2.3002

Max Act: 1.9290. Min Act: -0.0000

Data Index: 975157 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 2.3002. Min Range: -2.3002

Max Act: 1.7671. Min Act: -0.0000

Data Index: 397687 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 2.3002. Min Range: -2.3002

Max Act: 1.6803. Min Act: -0.0000

Data Index: 336292 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 2.3002. Min Range: -2.3002

Max Act: 1.8485. Min Act: -0.0000

Data Index: 171655 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 2.3002. Min Range: -2.3002

Max Act: 1.7170. Min Act: -0.0000

Data Index: 91353 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 2.3002. Min Range: -2.3002

Max Act: 1.6216. Min Act: -0.0000

Data Index: 865438 (C4 (Web Text))

Max Activating Token Index: 903