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

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

Neuron 1921 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0003

Data Index: 958772 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0733. Min Act: -0.0004

Data Index: 844707 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0724. Min Act: -0.0003

Data Index: 421483 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0717. Min Act: -0.0004

Data Index: 585426 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0697. Min Act: -0.0003

Data Index: 72926 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0693. Min Act: -0.0004

Data Index: 161106 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0632. Min Act: -0.0004

Data Index: 794174 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0646. Min Act: -0.0004

Data Index: 190541 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0632. Min Act: -0.0003

Data Index: 164805 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0636. Min Act: -0.0003

Data Index: 522386 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0633. Min Act: -0.0004

Data Index: 42887 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0627. Min Act: -0.0004

Data Index: 900478 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0605. Min Act: -0.0003

Data Index: 1334261 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0616. Min Act: -0.0004

Data Index: 200079 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0596. Min Act: -0.0003

Data Index: 663236 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0606. Min Act: -0.0003

Data Index: 380238 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0613. Min Act: -0.0003

Data Index: 989715 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0588. Min Act: -0.0004

Data Index: 1011090 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0591. Min Act: -0.0003

Data Index: 1198539 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0597. Min Act: -0.0004

Data Index: 1020387 (C4 (Web Text))

Max Activating Token Index: 462