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

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

Neuron 718 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: 1.3992. Min Range: -1.3992

Max Act: 1.3992. Min Act: 0.0000

Data Index: 1326970 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.3930. Min Act: -0.0000

Data Index: 457385 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1358968 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1088935 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.0584. Min Act: 0.0000

Data Index: 722362 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.0165. Min Act: 0.0000

Data Index: 882263 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.0110. Min Act: -0.0000

Data Index: 590469 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.9891. Min Act: 0.0000

Data Index: 443465 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 1.3992. Min Range: -1.3992

Max Act: 1.0412. Min Act: -0.0000

Data Index: 315556 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.9439. Min Act: -0.0000

Data Index: 732660 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.9156. Min Act: -0.0000

Data Index: 224447 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.9685. Min Act: 0.0001

Data Index: 209821 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.9101. Min Act: 0.0000

Data Index: 357797 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.9812. Min Act: -0.0000

Data Index: 754450 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.8935. Min Act: 0.0000

Data Index: 465447 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.9419. Min Act: 0.0000

Data Index: 245796 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.9486. Min Act: 0.0000

Data Index: 250233 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.9891. Min Act: -0.0000

Data Index: 247905 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.8350. Min Act: -0.0000

Data Index: 248018 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 1.3992. Min Range: -1.3992

Max Act: 0.9168. Min Act: 0.0000

Data Index: 1302390 (C4 (Web Text))

Max Activating Token Index: 731