Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1742 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.7460. Min Act: -0.0003

Data Index: 223344 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.6477. Min Act: -0.0003

Data Index: 285629 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.6492. Min Act: -0.0003

Data Index: 448836 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.6263. Min Act: -0.0003

Data Index: 433305 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5948. Min Act: -0.0002

Data Index: 1155537 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5341. Min Act: -0.0003

Data Index: 182102 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5525. Min Act: -0.0003

Data Index: 195197 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5631. Min Act: -0.0002

Data Index: 693579 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5525. Min Act: -0.0003

Data Index: 200354 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5718. Min Act: -0.0003

Data Index: 472942 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5863. Min Act: -0.0003

Data Index: 331300 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.6191. Min Act: -0.0003

Data Index: 539580 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5412. Min Act: -0.0002

Data Index: 617649 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5013. Min Act: -0.0003

Data Index: 906129 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5139. Min Act: -0.0003

Data Index: 1308564 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5308. Min Act: -0.0002

Data Index: 675044 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5800. Min Act: -0.0002

Data Index: 1303159 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5219. Min Act: -0.0003

Data Index: 525922 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.5451. Min Act: -0.0003

Data Index: 76673 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.7460. Min Range: -0.7460

Max Act: 0.4941. Min Act: -0.0003

Data Index: 5407 (C4 (Web Text))

Max Activating Token Index: 102