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

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

Neuron 4477 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.2843. Min Act: -0.0000

Data Index: 356142 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.7088. Min Act: -0.0000

Data Index: 95239 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.8047. Min Act: -0.0000

Data Index: 666517 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.6235. Min Act: -0.0000

Data Index: 355901 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.5363. Min Act: -0.0000

Data Index: 1332219 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.4819. Min Act: -0.0000

Data Index: 74621 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.4488. Min Act: -0.0000

Data Index: 160070 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 2.8047. Min Range: -2.8047

Max Act: 1.7161. Min Act: -0.0000

Data Index: 398602 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.1905. Min Act: -0.0000

Data Index: 816717 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.4237. Min Act: -0.0000

Data Index: 66490 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.4315. Min Act: -0.0000

Data Index: 1263742 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.3721. Min Act: -0.0000

Data Index: 386964 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.0861. Min Act: -0.0000

Data Index: 957856 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.1727. Min Act: -0.0000

Data Index: 1090215 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.2519. Min Act: -0.0000

Data Index: 173539 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.2494. Min Act: -0.0000

Data Index: 1061192 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.1047. Min Act: -0.0000

Data Index: 565940 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.2150. Min Act: -0.0000

Data Index: 53795 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.1533. Min Act: -0.0000

Data Index: 998964 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 2.8047. Min Range: -2.8047

Max Act: 2.0328. Min Act: -0.0000

Data Index: 611509 (C4 (Web Text))

Max Activating Token Index: 552