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

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

Neuron 481 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.5313. Min Act: -0.0001

Data Index: 277194 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.5309. Min Act: -0.0001

Data Index: 583380 (C4 (Web Text))

Max Activating Token Index: 408

Text #2

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.5138. Min Act: -0.0001

Data Index: 692671 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4787. Min Act: -0.0001

Data Index: 300493 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4789. Min Act: -0.0001

Data Index: 353696 (C4 (Web Text))

Max Activating Token Index: 392

Text #5

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4720. Min Act: -0.0001

Data Index: 135880 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4841. Min Act: -0.0001

Data Index: 801846 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4794. Min Act: -0.0001

Data Index: 627829 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4740. Min Act: -0.0001

Data Index: 483069 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4738. Min Act: -0.0000

Data Index: 722353 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4678. Min Act: -0.0001

Data Index: 1300401 (C4 (Web Text))

Max Activating Token Index: 165

Text #11

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4543. Min Act: -0.0000

Data Index: 141910 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4817. Min Act: -0.0001

Data Index: 948976 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4627. Min Act: -0.0001

Data Index: 1157189 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4616. Min Act: -0.0001

Data Index: 447898 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4637. Min Act: -0.0000

Data Index: 440526 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4482. Min Act: -0.0001

Data Index: 279832 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4604. Min Act: -0.0001

Data Index: 985073 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4393. Min Act: -0.0001

Data Index: 10745 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4517. Min Act: -0.0001

Data Index: 81826 (C4 (Web Text))

Max Activating Token Index: 938