Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 543 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0002

Data Index: 561283 (C4 (Web Text))

Max Activating Token Index: 794

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0716. Min Act: -0.0002

Data Index: 154371 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0654. Min Act: -0.0002

Data Index: 396952 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0714. Min Act: -0.0002

Data Index: 821883 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0700. Min Act: -0.0002

Data Index: 956058 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1252940 (C4 (Web Text))

Max Activating Token Index: 892

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0686. Min Act: -0.0002

Data Index: 825852 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0699. Min Act: -0.0002

Data Index: 405152 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0686. Min Act: -0.0002

Data Index: 619856 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0656. Min Act: -0.0002

Data Index: 179851 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0667. Min Act: -0.0002

Data Index: 52741 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0646. Min Act: -0.0002

Data Index: 534287 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1146331 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0663. Min Act: -0.0002

Data Index: 80203 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0694. Min Act: -0.0002

Data Index: 621379 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1102502 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0627. Min Act: -0.0002

Data Index: 1307044 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0645. Min Act: -0.0002

Data Index: 802551 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1111491 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0639. Min Act: -0.0002

Data Index: 787074 (C4 (Web Text))

Max Activating Token Index: 406