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

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

Neuron 3685 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.6265. Min Act: -0.0003

Data Index: 388484 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.6319. Min Act: -0.0002

Data Index: 161326 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.6357. Min Act: -0.0003

Data Index: 987351 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.6559. Min Act: -0.0003

Data Index: 1345270 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.6165. Min Act: -0.0003

Data Index: 359738 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.6085. Min Act: -0.0002

Data Index: 1111715 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.6102. Min Act: -0.0003

Data Index: 936493 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5939. Min Act: -0.0003

Data Index: 1273535 (C4 (Web Text))

Max Activating Token Index: 318

Text #8

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5664. Min Act: -0.0003

Data Index: 277720 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5790. Min Act: -0.0003

Data Index: 1077550 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5919. Min Act: -0.0003

Data Index: 308400 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5885. Min Act: -0.0003

Data Index: 179591 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5671. Min Act: -0.0003

Data Index: 1131226 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5634. Min Act: -0.0002

Data Index: 122309 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5637. Min Act: -0.0003

Data Index: 326126 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5567. Min Act: -0.0003

Data Index: 762001 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5607. Min Act: -0.0003

Data Index: 815869 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5540. Min Act: -0.0003

Data Index: 1154421 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5543. Min Act: -0.0003

Data Index: 706891 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.6559. Min Range: -0.6559

Max Act: 0.5514. Min Act: -0.0003

Data Index: 941920 (C4 (Web Text))

Max Activating Token Index: 249