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

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

Neuron 799 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1213. Min Range: -1.1213

Max Act: 1.1213. Min Act: -0.0001

Data Index: 2645 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.1213. Min Range: -1.1213

Max Act: 1.0745. Min Act: -0.0001

Data Index: 765764 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 1.1213. Min Range: -1.1213

Max Act: 1.0266. Min Act: -0.0001

Data Index: 176626 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 1.1213. Min Range: -1.1213

Max Act: 1.0334. Min Act: -0.0001

Data Index: 781571 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.9848. Min Act: -0.0001

Data Index: 1033287 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.9562. Min Act: -0.0001

Data Index: 819941 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.9462. Min Act: -0.0001

Data Index: 525451 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.9188. Min Act: -0.0001

Data Index: 1058211 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8744. Min Act: -0.0001

Data Index: 457034 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.9486. Min Act: -0.0001

Data Index: 424790 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8910. Min Act: -0.0001

Data Index: 843082 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.9098. Min Act: -0.0001

Data Index: 1108315 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8572. Min Act: -0.0001

Data Index: 133508 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.7973. Min Act: -0.0001

Data Index: 84720 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8810. Min Act: -0.0001

Data Index: 255343 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8237. Min Act: -0.0001

Data Index: 366309 (C4 (Web Text))

Max Activating Token Index: 165

Text #16

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8219. Min Act: -0.0001

Data Index: 610296 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8999. Min Act: -0.0001

Data Index: 274280 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8194. Min Act: -0.0001

Data Index: 582626 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 1.1213. Min Range: -1.1213

Max Act: 0.8634. Min Act: -0.0001

Data Index: 722602 (C4 (Web Text))

Max Activating Token Index: 320