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

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

Neuron 933 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1805. Min Act: -0.0000

Data Index: 499001 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1759. Min Act: -0.0000

Data Index: 179878 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1086956 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1704. Min Act: -0.0000

Data Index: 769229 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1639. Min Act: -0.0000

Data Index: 412837 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1697. Min Act: 0.0000

Data Index: 67203 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1613. Min Act: -0.0001

Data Index: 499135 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1603. Min Act: -0.0000

Data Index: 647804 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1516. Min Act: -0.0001

Data Index: 580469 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1519. Min Act: -0.0000

Data Index: 1277147 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1380. Min Act: -0.0000

Data Index: 9580 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1404. Min Act: -0.0000

Data Index: 96852 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1375. Min Act: -0.0000

Data Index: 543442 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1319. Min Act: -0.0000

Data Index: 1211333 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1365. Min Act: -0.0000

Data Index: 896722 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1252. Min Act: -0.0000

Data Index: 247671 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1240. Min Act: -0.0000

Data Index: 516824 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1257. Min Act: -0.0001

Data Index: 1343332 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1277. Min Act: -0.0000

Data Index: 975435 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.1805. Min Range: -0.1805

Max Act: 0.1216. Min Act: -0.0000

Data Index: 168523 (C4 (Web Text))

Max Activating Token Index: 491