Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1898 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.8048. Min Act: -0.0001

Data Index: 620376 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.8200. Min Act: -0.0000

Data Index: 515049 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1059220 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7824. Min Act: -0.0000

Data Index: 165669 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1028036 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7632. Min Act: -0.0001

Data Index: 805372 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7640. Min Act: -0.0001

Data Index: 858080 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7715. Min Act: -0.0001

Data Index: 1091549 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7727. Min Act: -0.0000

Data Index: 655184 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6991. Min Act: -0.0000

Data Index: 640489 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7030. Min Act: -0.0000

Data Index: 1316038 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7187. Min Act: -0.0000

Data Index: 114001 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7370. Min Act: -0.0000

Data Index: 259458 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7555. Min Act: -0.0000

Data Index: 377846 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7262. Min Act: -0.0000

Data Index: 278524 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7495. Min Act: -0.0000

Data Index: 616694 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7504. Min Act: -0.0000

Data Index: 831830 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6992. Min Act: -0.0000

Data Index: 841297 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.6805. Min Act: -0.0000

Data Index: 961487 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.8311. Min Range: -0.8311

Max Act: 0.7230. Min Act: -0.0000

Data Index: 965685 (C4 (Web Text))

Max Activating Token Index: 240