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

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

Neuron 200 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1905. Min Act: -0.0002

Data Index: 926762 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1638. Min Act: -0.0001

Data Index: 976557 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1563. Min Act: -0.0002

Data Index: 64404 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1576. Min Act: -0.0001

Data Index: 302305 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1411. Min Act: -0.0002

Data Index: 850982 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1458. Min Act: -0.0001

Data Index: 188390 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1441. Min Act: -0.0001

Data Index: 683286 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1415. Min Act: -0.0001

Data Index: 167113 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1351. Min Act: -0.0001

Data Index: 580416 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1371. Min Act: -0.0001

Data Index: 431919 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1302. Min Act: -0.0001

Data Index: 217580 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1250. Min Act: -0.0002

Data Index: 1271592 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1219. Min Act: -0.0002

Data Index: 1323670 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1251. Min Act: -0.0002

Data Index: 991072 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1193. Min Act: -0.0001

Data Index: 529054 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1204. Min Act: -0.0001

Data Index: 1148605 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1115. Min Act: -0.0001

Data Index: 244844 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1077. Min Act: -0.0002

Data Index: 1119308 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1175. Min Act: -0.0002

Data Index: 596677 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.1905. Min Range: -0.1905

Max Act: 0.1107. Min Act: -0.0001

Data Index: 845563 (C4 (Web Text))

Max Activating Token Index: 566