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

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

Neuron 5353 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.5845. Min Act: -0.0000

Data Index: 223525 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.5316. Min Act: -0.0000

Data Index: 847169 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.4250. Min Act: -0.0000

Data Index: 250688 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.4991. Min Act: -0.0000

Data Index: 459440 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.3240. Min Act: -0.0000

Data Index: 1268089 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.2219. Min Act: -0.0000

Data Index: 1304297 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.3296. Min Act: -0.0000

Data Index: 871457 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.2723. Min Act: -0.0000

Data Index: 1650169 (Python Code)

Max Activating Token Index: 865

Text #8

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.3079. Min Act: -0.0000

Data Index: 1098135 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1924. Min Act: -0.0000

Data Index: 1328793 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1626. Min Act: -0.0000

Data Index: 767140 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1257. Min Act: -0.0000

Data Index: 1241332 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.2005. Min Act: -0.0000

Data Index: 687743 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1328. Min Act: -0.0000

Data Index: 655780 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1490. Min Act: -0.0000

Data Index: 32558 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1086. Min Act: -0.0000

Data Index: 917574 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1126. Min Act: -0.0000

Data Index: 1115800 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1066929 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1625. Min Act: -0.0000

Data Index: 1029256 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 1.5845. Min Range: -1.5845

Max Act: 1.1233. Min Act: -0.0000

Data Index: 155135 (C4 (Web Text))

Max Activating Token Index: 109