Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 437 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.1205. Min Act: -0.0002

Data Index: 159951 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0765. Min Act: -0.0002

Data Index: 477974 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1345445 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0711. Min Act: -0.0002

Data Index: 599820 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0684. Min Act: -0.0002

Data Index: 781137 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0657. Min Act: -0.0002

Data Index: 419898 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0663. Min Act: -0.0002

Data Index: 871606 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0624. Min Act: -0.0002

Data Index: 792050 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0647. Min Act: -0.0002

Data Index: 585304 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0609. Min Act: -0.0002

Data Index: 563552 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0601. Min Act: -0.0002

Data Index: 949296 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1175450 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0571. Min Act: -0.0002

Data Index: 840884 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1289703 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0596. Min Act: -0.0002

Data Index: 338476 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0582. Min Act: -0.0002

Data Index: 948567 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0583. Min Act: -0.0002

Data Index: 695638 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0586. Min Act: -0.0002

Data Index: 968433 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0577. Min Act: -0.0002

Data Index: 55126 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 0.1205. Min Range: -0.1205

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1172152 (C4 (Web Text))

Max Activating Token Index: 1014