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

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

Neuron 2006 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: 5.8060. Min Range: -5.8060

Max Act: 5.8060. Min Act: -0.0000

Data Index: 178486 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 5.8060. Min Range: -5.8060

Max Act: 5.6342. Min Act: -0.0000

Data Index: 177705 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 5.8060. Min Range: -5.8060

Max Act: 5.6096. Min Act: -0.0000

Data Index: 949913 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 5.8060. Min Range: -5.8060

Max Act: 5.5365. Min Act: -0.0000

Data Index: 707038 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 5.8060. Min Range: -5.8060

Max Act: 5.3261. Min Act: -0.0000

Data Index: 640271 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 5.8060. Min Range: -5.8060

Max Act: 5.2556. Min Act: -0.0000

Data Index: 759368 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 5.8060. Min Range: -5.8060

Max Act: 5.6122. Min Act: -0.0000

Data Index: 1255443 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 5.8060. Min Range: -5.8060

Max Act: 5.0460. Min Act: -0.0000

Data Index: 60350 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 5.8060. Min Range: -5.8060

Max Act: 5.2003. Min Act: -0.0000

Data Index: 1029934 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 5.8060. Min Range: -5.8060

Max Act: 5.1680. Min Act: -0.0000

Data Index: 884219 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 5.8060. Min Range: -5.8060

Max Act: 5.1484. Min Act: -0.0000

Data Index: 436369 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 5.8060. Min Range: -5.8060

Max Act: 4.9535. Min Act: -0.0000

Data Index: 687184 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 5.8060. Min Range: -5.8060

Max Act: 5.3188. Min Act: -0.0000

Data Index: 496468 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 5.8060. Min Range: -5.8060

Max Act: 4.9269. Min Act: -0.0000

Data Index: 580156 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 5.8060. Min Range: -5.8060

Max Act: 5.1097. Min Act: -0.0000

Data Index: 29020 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 5.8060. Min Range: -5.8060

Max Act: 5.0932. Min Act: -0.0000

Data Index: 492048 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 5.8060. Min Range: -5.8060

Max Act: 4.8289. Min Act: -0.0000

Data Index: 671587 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 5.8060. Min Range: -5.8060

Max Act: 5.0171. Min Act: -0.0000

Data Index: 828078 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 5.8060. Min Range: -5.8060

Max Act: 5.0187. Min Act: -0.0000

Data Index: 1275934 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 5.8060. Min Range: -5.8060

Max Act: 4.8058. Min Act: -0.0000

Data Index: 9544 (C4 (Web Text))

Max Activating Token Index: 932