Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1308 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6240. Min Act: -0.0003

Data Index: 882726 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.7116. Min Act: -0.0003

Data Index: 411097 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6627. Min Act: -0.0003

Data Index: 373236 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6111. Min Act: -0.0003

Data Index: 18345 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6598. Min Act: -0.0003

Data Index: 1040633 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6172. Min Act: -0.0003

Data Index: 1187265 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6180. Min Act: -0.0003

Data Index: 335659 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.6116. Min Act: -0.0003

Data Index: 71409 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5452. Min Act: -0.0003

Data Index: 1111775 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5698. Min Act: -0.0003

Data Index: 527656 (C4 (Web Text))

Max Activating Token Index: 189

Text #10

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5685. Min Act: -0.0003

Data Index: 409644 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4828. Min Act: -0.0003

Data Index: 760501 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5405. Min Act: -0.0003

Data Index: 1123813 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5606. Min Act: -0.0003

Data Index: 225909 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5687. Min Act: -0.0003

Data Index: 528727 (C4 (Web Text))

Max Activating Token Index: 328

Text #15

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5573. Min Act: -0.0003

Data Index: 1227968 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5449. Min Act: -0.0003

Data Index: 729112 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5148. Min Act: -0.0003

Data Index: 1074635 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.5103. Min Act: -0.0003

Data Index: 606184 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.7116. Min Range: -0.7116

Max Act: 0.4717. Min Act: -0.0003

Data Index: 736850 (C4 (Web Text))

Max Activating Token Index: 73