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

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

Neuron 4888 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2467. Min Range: -1.2467

Max Act: 1.2467. Min Act: -0.0000

Data Index: 111945 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 1.2467. Min Range: -1.2467

Max Act: 1.1676. Min Act: -0.0000

Data Index: 1040627 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 1.2467. Min Range: -1.2467

Max Act: 1.1549. Min Act: -0.0000

Data Index: 812569 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.2467. Min Range: -1.2467

Max Act: 1.0697. Min Act: -0.0000

Data Index: 205354 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 1.2467. Min Range: -1.2467

Max Act: 1.0476. Min Act: -0.0000

Data Index: 325046 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 1.2467. Min Range: -1.2467

Max Act: 1.0812. Min Act: -0.0000

Data Index: 609279 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.2467. Min Range: -1.2467

Max Act: 1.0581. Min Act: -0.0000

Data Index: 775356 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.2467. Min Range: -1.2467

Max Act: 0.9996. Min Act: -0.0000

Data Index: 1035591 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 1.2467. Min Range: -1.2467

Max Act: 0.9807. Min Act: -0.0000

Data Index: 864999 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 1.2467. Min Range: -1.2467

Max Act: 0.9868. Min Act: -0.0000

Data Index: 592093 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 1.2467. Min Range: -1.2467

Max Act: 0.9994. Min Act: -0.0000

Data Index: 838218 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 1.2467. Min Range: -1.2467

Max Act: 1.0172. Min Act: -0.0000

Data Index: 308360 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 1.2467. Min Range: -1.2467

Max Act: 0.9255. Min Act: -0.0000

Data Index: 482323 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 1.2467. Min Range: -1.2467

Max Act: 0.9504. Min Act: -0.0000

Data Index: 777071 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 1.2467. Min Range: -1.2467

Max Act: 0.9906. Min Act: -0.0000

Data Index: 1261393 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 1.2467. Min Range: -1.2467

Max Act: 0.9371. Min Act: -0.0000

Data Index: 218990 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 1.2467. Min Range: -1.2467

Max Act: 0.9585. Min Act: -0.0000

Data Index: 966709 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 1.2467. Min Range: -1.2467

Max Act: 0.8963. Min Act: -0.0000

Data Index: 223990 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 1.2467. Min Range: -1.2467

Max Act: 0.9422. Min Act: -0.0000

Data Index: 107451 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 1.2467. Min Range: -1.2467

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1099620 (C4 (Web Text))

Max Activating Token Index: 51