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

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

Neuron 2066 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.1046. Min Act: -0.0002

Data Index: 978284 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1316206 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0928. Min Act: -0.0002

Data Index: 201338 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0904. Min Act: -0.0002

Data Index: 945677 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1249905 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1092546 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0842. Min Act: -0.0002

Data Index: 58099 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1042226 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0810. Min Act: -0.0002

Data Index: 276412 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0820. Min Act: -0.0002

Data Index: 749735 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1049272 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0840. Min Act: -0.0002

Data Index: 455028 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0809. Min Act: -0.0002

Data Index: 742214 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0769. Min Act: -0.0002

Data Index: 728975 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0759. Min Act: -0.0002

Data Index: 812642 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0749. Min Act: -0.0002

Data Index: 869355 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1376070 (Python Code)

Max Activating Token Index: 540

Text #17

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0742. Min Act: -0.0002

Data Index: 576262 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0732. Min Act: -0.0002

Data Index: 942716 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0735. Min Act: -0.0002

Data Index: 135182 (C4 (Web Text))

Max Activating Token Index: 388