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

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

Neuron 4749 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1116. Min Range: -2.1116

Max Act: 2.1116. Min Act: -0.0000

Data Index: 991372 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.8589. Min Act: -0.0000

Data Index: 1302165 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.9503. Min Act: -0.0000

Data Index: 438066 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.8540. Min Act: -0.0000

Data Index: 590110 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.9354. Min Act: -0.0000

Data Index: 1097352 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.9024. Min Act: -0.0000

Data Index: 91539 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.8111. Min Act: -0.0000

Data Index: 683829 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.8001. Min Act: -0.0000

Data Index: 397435 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.6027. Min Act: -0.0000

Data Index: 882199 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.5884. Min Act: -0.0000

Data Index: 164941 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.4808. Min Act: -0.0000

Data Index: 271105 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.4360. Min Act: -0.0000

Data Index: 411899 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.4765. Min Act: -0.0000

Data Index: 320064 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.4030. Min Act: -0.0000

Data Index: 257520 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.4136. Min Act: -0.0000

Data Index: 822299 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.3004. Min Act: -0.0000

Data Index: 468340 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.3586. Min Act: -0.0000

Data Index: 1126688 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.1528. Min Act: -0.0000

Data Index: 1245572 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.3080. Min Act: -0.0000

Data Index: 989682 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 2.1116. Min Range: -2.1116

Max Act: 1.1652. Min Act: -0.0000

Data Index: 358132 (C4 (Web Text))

Max Activating Token Index: 201