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

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

Neuron 3954 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: 0.0788. Min Range: -0.0788

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1104976 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0788. Min Act: -0.0002

Data Index: 152739 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0724. Min Act: -0.0002

Data Index: 1213676 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0773. Min Act: -0.0002

Data Index: 355820 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1163884 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0642. Min Act: -0.0002

Data Index: 663579 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1049635 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0631. Min Act: -0.0003

Data Index: 617 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1020992 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0587. Min Act: -0.0002

Data Index: 658201 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0571. Min Act: -0.0002

Data Index: 34774 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0591. Min Act: -0.0002

Data Index: 638439 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1019738 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0544. Min Act: -0.0002

Data Index: 991578 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0537. Min Act: -0.0002

Data Index: 560837 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0534. Min Act: -0.0002

Data Index: 22371 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1258004 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0546. Min Act: -0.0002

Data Index: 814040 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0525. Min Act: -0.0002

Data Index: 928952 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0536. Min Act: -0.0002

Data Index: 715443 (C4 (Web Text))

Max Activating Token Index: 338