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

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

Neuron 1994 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: 1.5973. Min Range: -1.5973

Max Act: 1.5973. Min Act: -0.0001

Data Index: 641563 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 1.5973. Min Range: -1.5973

Max Act: 1.3264. Min Act: -0.0001

Data Index: 303801 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 1.5973. Min Range: -1.5973

Max Act: 1.2623. Min Act: -0.0001

Data Index: 349576 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 1.5973. Min Range: -1.5973

Max Act: 1.2020. Min Act: -0.0001

Data Index: 168623 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 1.5973. Min Range: -1.5973

Max Act: 1.0380. Min Act: -0.0001

Data Index: 772939 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 1.5973. Min Range: -1.5973

Max Act: 1.1209. Min Act: -0.0001

Data Index: 1016907 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 1.5973. Min Range: -1.5973

Max Act: 1.0855. Min Act: -0.0001

Data Index: 446224 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 1.5973. Min Range: -1.5973

Max Act: 1.0731. Min Act: -0.0001

Data Index: 220597 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 1.5973. Min Range: -1.5973

Max Act: 1.0575. Min Act: -0.0001

Data Index: 697589 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 1.5973. Min Range: -1.5973

Max Act: 1.1405. Min Act: -0.0001

Data Index: 796810 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 1.5973. Min Range: -1.5973

Max Act: 1.0575. Min Act: -0.0001

Data Index: 590748 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 1.5973. Min Range: -1.5973

Max Act: 1.1134. Min Act: -0.0001

Data Index: 861538 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 1.5973. Min Range: -1.5973

Max Act: 1.1163. Min Act: -0.0001

Data Index: 317608 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 1.5973. Min Range: -1.5973

Max Act: 1.0396. Min Act: -0.0001

Data Index: 404164 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 1.5973. Min Range: -1.5973

Max Act: 1.0529. Min Act: -0.0001

Data Index: 526076 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 1.5973. Min Range: -1.5973

Max Act: 0.9976. Min Act: -0.0001

Data Index: 815062 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 1.5973. Min Range: -1.5973

Max Act: 0.9366. Min Act: -0.0001

Data Index: 515737 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 1.5973. Min Range: -1.5973

Max Act: 0.9879. Min Act: -0.0001

Data Index: 1302251 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 1.5973. Min Range: -1.5973

Max Act: 0.9825. Min Act: -0.0001

Data Index: 500788 (C4 (Web Text))

Max Activating Token Index: 417

Text #19

Max Range: 1.5973. Min Range: -1.5973

Max Act: 0.9498. Min Act: -0.0001

Data Index: 772226 (C4 (Web Text))

Max Activating Token Index: 718