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

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

Neuron 1661 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.8106. Min Act: -0.0000

Data Index: 213676 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1243508 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4918. Min Act: -0.0000

Data Index: 287799 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4687. Min Act: -0.0000

Data Index: 475249 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4763. Min Act: -0.0000

Data Index: 1036851 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1085870 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4795. Min Act: -0.0000

Data Index: 361819 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4497. Min Act: -0.0000

Data Index: 891144 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4564. Min Act: -0.0000

Data Index: 813914 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4551. Min Act: -0.0000

Data Index: 85115 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4562. Min Act: -0.0000

Data Index: 620275 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1276610 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4034. Min Act: -0.0000

Data Index: 683662 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.3985. Min Act: -0.0000

Data Index: 14153 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4132. Min Act: -0.0000

Data Index: 358123 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4464. Min Act: -0.0000

Data Index: 174039 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4217. Min Act: -0.0000

Data Index: 311129 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4515. Min Act: -0.0000

Data Index: 677754 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4104. Min Act: -0.0000

Data Index: 417011 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4226. Min Act: -0.0000

Data Index: 336242 (C4 (Web Text))

Max Activating Token Index: 873