Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 807 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0720. Min Act: -0.0006

Data Index: 245227 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0687. Min Act: -0.0006

Data Index: 147451 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0697. Min Act: -0.0006

Data Index: 558391 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0691. Min Act: -0.0006

Data Index: 300048 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0655. Min Act: -0.0006

Data Index: 389327 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0656. Min Act: -0.0006

Data Index: 1223134 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0651. Min Act: -0.0006

Data Index: 185423 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0676. Min Act: -0.0006

Data Index: 693403 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0659. Min Act: -0.0006

Data Index: 1025147 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0655. Min Act: -0.0006

Data Index: 138844 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0656. Min Act: -0.0006

Data Index: 132249 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0666. Min Act: -0.0006

Data Index: 113785 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0664. Min Act: -0.0006

Data Index: 687798 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0657. Min Act: -0.0006

Data Index: 61250 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0612. Min Act: -0.0006

Data Index: 775170 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0613. Min Act: -0.0006

Data Index: 1254 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0620. Min Act: -0.0006

Data Index: 1172213 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0631. Min Act: -0.0006

Data Index: 1078828 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0642. Min Act: -0.0006

Data Index: 352250 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.0720. Min Range: -0.0720

Max Act: 0.0642. Min Act: -0.0006

Data Index: 858201 (C4 (Web Text))

Max Activating Token Index: 553