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

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

Neuron 784 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0786. Min Act: -0.0002

Data Index: 953230 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1336130 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0739. Min Act: -0.0002

Data Index: 946044 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0810. Min Act: -0.0002

Data Index: 170518 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0627. Min Act: -0.0002

Data Index: 713610 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0662. Min Act: -0.0002

Data Index: 988744 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0653. Min Act: -0.0002

Data Index: 448315 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0709. Min Act: -0.0002

Data Index: 478644 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0742. Min Act: -0.0002

Data Index: 146456 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0685. Min Act: -0.0002

Data Index: 928161 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0707. Min Act: -0.0002

Data Index: 386253 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0726. Min Act: -0.0002

Data Index: 95364 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0669. Min Act: -0.0002

Data Index: 245841 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1254440 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0705. Min Act: -0.0002

Data Index: 451379 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1067700 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0675. Min Act: -0.0002

Data Index: 456785 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0660. Min Act: -0.0002

Data Index: 21899 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0656. Min Act: -0.0002

Data Index: 485606 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0492. Min Act: -0.0002

Data Index: 629059 (C4 (Web Text))

Max Activating Token Index: 650