Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3378 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.2242. Min Act: -0.0000

Data Index: 1241557 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.1760. Min Act: -0.0000

Data Index: 505427 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.0683. Min Act: -0.0000

Data Index: 746262 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 1.2242. Min Range: -1.2242

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1255468 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9807. Min Act: -0.0000

Data Index: 1210278 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9122. Min Act: -0.0000

Data Index: 370997 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9665. Min Act: -0.0000

Data Index: 852530 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9056. Min Act: -0.0000

Data Index: 350644 (C4 (Web Text))

Max Activating Token Index: 566

Text #8

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.9456. Min Act: -0.0000

Data Index: 15895 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8397. Min Act: -0.0000

Data Index: 46773 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8986. Min Act: -0.0000

Data Index: 556184 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8503. Min Act: -0.0000

Data Index: 22116 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8083. Min Act: -0.0000

Data Index: 854750 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8478. Min Act: -0.0000

Data Index: 390302 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8833. Min Act: -0.0000

Data Index: 516988 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7846. Min Act: -0.0000

Data Index: 321677 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7640. Min Act: -0.0000

Data Index: 880597 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8202. Min Act: -0.0000

Data Index: 402618 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.8558. Min Act: -0.0000

Data Index: 910461 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 1.2242. Min Range: -1.2242

Max Act: 0.7946. Min Act: -0.0000

Data Index: 782530 (C4 (Web Text))

Max Activating Token Index: 880