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

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

Neuron 1646 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.7297. Min Act: -0.0000

Data Index: 504684 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1171716 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5913. Min Act: -0.0000

Data Index: 546671 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5788. Min Act: -0.0000

Data Index: 467152 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5730. Min Act: -0.0000

Data Index: 785116 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5657. Min Act: -0.0000

Data Index: 691545 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1331299 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5080. Min Act: -0.0000

Data Index: 144777 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4957. Min Act: -0.0000

Data Index: 266810 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5368. Min Act: -0.0000

Data Index: 764795 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5039. Min Act: -0.0000

Data Index: 682577 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5190. Min Act: -0.0000

Data Index: 629086 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5107. Min Act: -0.0000

Data Index: 111305 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.5435. Min Act: -0.0000

Data Index: 239277 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4979. Min Act: -0.0000

Data Index: 605525 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4671. Min Act: -0.0000

Data Index: 200552 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4800. Min Act: -0.0000

Data Index: 71482 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1286284 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4526. Min Act: -0.0000

Data Index: 492002 (C4 (Web Text))

Max Activating Token Index: 825

Text #19

Max Range: 0.7297. Min Range: -0.7297

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1078803 (C4 (Web Text))

Max Activating Token Index: 77