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

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

Neuron 5472 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2660. Min Act: -0.0000

Data Index: 450637 (C4 (Web Text))

Max Activating Token Index: 625

Text #1

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1206564 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2459. Min Act: -0.0000

Data Index: 107934 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1184253 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2325. Min Act: 0.0000

Data Index: 1008003 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1003629 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2236. Min Act: -0.0000

Data Index: 363302 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2211. Min Act: -0.0000

Data Index: 918775 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2040. Min Act: -0.0000

Data Index: 341509 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2117. Min Act: -0.0000

Data Index: 710924 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1014604 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2215. Min Act: 0.0000

Data Index: 1159072 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2148. Min Act: -0.0000

Data Index: 1347013 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1207519 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1303732 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2082. Min Act: -0.0000

Data Index: 210529 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2082. Min Act: -0.0000

Data Index: 176838 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2052. Min Act: -0.0000

Data Index: 315920 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1984. Min Act: -0.0000

Data Index: 228855 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2035. Min Act: -0.0000

Data Index: 732912 (C4 (Web Text))

Max Activating Token Index: 388