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

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

Neuron 2015 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1250247 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1229294 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0758. Min Act: -0.0002

Data Index: 739614 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0739. Min Act: -0.0002

Data Index: 121545 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1332921 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0718. Min Act: -0.0002

Data Index: 324151 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0687. Min Act: -0.0002

Data Index: 577750 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0688. Min Act: -0.0002

Data Index: 901101 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0679. Min Act: -0.0002

Data Index: 90226 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0686. Min Act: -0.0002

Data Index: 603386 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0682. Min Act: -0.0002

Data Index: 561311 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0668. Min Act: -0.0002

Data Index: 21431 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0668. Min Act: -0.0002

Data Index: 681440 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1499330 (Python Code)

Max Activating Token Index: 814

Text #14

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0681. Min Act: -0.0002

Data Index: 164347 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0670. Min Act: -0.0002

Data Index: 32691 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0644. Min Act: -0.0002

Data Index: 442011 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0642. Min Act: -0.0002

Data Index: 104534 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0650. Min Act: -0.0002

Data Index: 420747 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0661. Min Act: -0.0002

Data Index: 695309 (C4 (Web Text))

Max Activating Token Index: 838