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

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

Neuron 3548 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1149. Min Act: 0.0000

Data Index: 748158 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1234. Min Act: -0.0000

Data Index: 579985 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.1043. Min Act: 0.0000

Data Index: 1086760 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0970. Min Act: -0.0000

Data Index: 825854 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0958. Min Act: -0.0000

Data Index: 160397 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0909. Min Act: -0.0000

Data Index: 1066846 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0850. Min Act: -0.0000

Data Index: 1143107 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0876. Min Act: -0.0000

Data Index: 979316 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0872. Min Act: -0.0000

Data Index: 1398282 (Python Code)

Max Activating Token Index: 238

Text #9

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0893. Min Act: -0.0000

Data Index: 454285 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0781. Min Act: -0.0000

Data Index: 659731 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0803. Min Act: -0.0000

Data Index: 894365 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0824. Min Act: 0.0000

Data Index: 832207 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0775. Min Act: -0.0000

Data Index: 68979 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0857. Min Act: -0.0000

Data Index: 648589 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0823. Min Act: -0.0000

Data Index: 921995 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0764. Min Act: -0.0000

Data Index: 616288 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0727. Min Act: -0.0000

Data Index: 1029223 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0741. Min Act: -0.0000

Data Index: 650502 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.1234. Min Range: -0.1234

Max Act: 0.0739. Min Act: -0.0000

Data Index: 131562 (C4 (Web Text))

Max Activating Token Index: 774