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

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

Neuron 4559 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1446615 (Python Code)

Max Activating Token Index: 780

Text #1

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1531261 (Python Code)

Max Activating Token Index: 592

Text #2

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1157. Min Act: -0.0000

Data Index: 477130 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1158. Min Act: -0.0000

Data Index: 524032 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1169. Min Act: -0.0000

Data Index: 1317055 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1111. Min Act: -0.0000

Data Index: 779013 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1083. Min Act: -0.0000

Data Index: 67867 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0948. Min Act: -0.0000

Data Index: 1460308 (Python Code)

Max Activating Token Index: 795

Text #8

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1066. Min Act: -0.0000

Data Index: 357019 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0992. Min Act: -0.0000

Data Index: 1544327 (Python Code)

Max Activating Token Index: 881

Text #10

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1040. Min Act: -0.0000

Data Index: 531425 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1445514 (Python Code)

Max Activating Token Index: 884

Text #12

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1011. Min Act: -0.0000

Data Index: 915830 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1383268 (Python Code)

Max Activating Token Index: 888

Text #14

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1030. Min Act: -0.0000

Data Index: 731698 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1593198 (Python Code)

Max Activating Token Index: 757

Text #16

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0958. Min Act: -0.0000

Data Index: 1336840 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1093. Min Act: -0.0000

Data Index: 1638690 (Python Code)

Max Activating Token Index: 849

Text #18

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1195491 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0969. Min Act: -0.0000

Data Index: 517735 (C4 (Web Text))

Max Activating Token Index: 490