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

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

Neuron 5422 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: 6.5344. Min Range: -6.5344

Max Act: 6.5344. Min Act: -0.0000

Data Index: 216136 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 6.5344. Min Range: -6.5344

Max Act: 5.9902. Min Act: -0.0000

Data Index: 816911 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 6.5344. Min Range: -6.5344

Max Act: 5.3264. Min Act: -0.0000

Data Index: 1141792 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 6.5344. Min Range: -6.5344

Max Act: 5.8787. Min Act: -0.0000

Data Index: 1015066 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 6.5344. Min Range: -6.5344

Max Act: 5.5930. Min Act: -0.0000

Data Index: 28309 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 6.5344. Min Range: -6.5344

Max Act: 5.5721. Min Act: -0.0000

Data Index: 1235908 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 6.5344. Min Range: -6.5344

Max Act: 5.5611. Min Act: -0.0000

Data Index: 1227776 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 6.5344. Min Range: -6.5344

Max Act: 5.0332. Min Act: -0.0000

Data Index: 42216 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 6.5344. Min Range: -6.5344

Max Act: 5.2344. Min Act: -0.0000

Data Index: 880780 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 6.5344. Min Range: -6.5344

Max Act: 5.1542. Min Act: -0.0000

Data Index: 234985 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 6.5344. Min Range: -6.5344

Max Act: 5.3750. Min Act: -0.0000

Data Index: 1056200 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 6.5344. Min Range: -6.5344

Max Act: 4.9744. Min Act: -0.0000

Data Index: 1304821 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 6.5344. Min Range: -6.5344

Max Act: 5.2130. Min Act: -0.0000

Data Index: 147614 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 6.5344. Min Range: -6.5344

Max Act: 5.0493. Min Act: -0.0000

Data Index: 1031305 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 6.5344. Min Range: -6.5344

Max Act: 4.6142. Min Act: -0.0000

Data Index: 328152 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 6.5344. Min Range: -6.5344

Max Act: 5.1550. Min Act: -0.0000

Data Index: 729440 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 6.5344. Min Range: -6.5344

Max Act: 4.7096. Min Act: -0.0000

Data Index: 189995 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 6.5344. Min Range: -6.5344

Max Act: 4.7048. Min Act: -0.0000

Data Index: 819695 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 6.5344. Min Range: -6.5344

Max Act: 4.5534. Min Act: -0.0000

Data Index: 416101 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 6.5344. Min Range: -6.5344

Max Act: 4.8544. Min Act: -0.0000

Data Index: 559699 (C4 (Web Text))

Max Activating Token Index: 330