Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4654 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0686. Min Act: -0.0002

Data Index: 470309 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0651. Min Act: -0.0002

Data Index: 5487 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0661. Min Act: -0.0002

Data Index: 989521 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0672. Min Act: -0.0003

Data Index: 661274 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0637. Min Act: -0.0003

Data Index: 1013057 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1352911 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1133666 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0633. Min Act: -0.0003

Data Index: 341685 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1246153 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0615. Min Act: -0.0002

Data Index: 612418 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0601. Min Act: -0.0003

Data Index: 267316 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0600. Min Act: -0.0002

Data Index: 596258 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0608. Min Act: -0.0002

Data Index: 664898 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1065903 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1231136 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0600. Min Act: -0.0002

Data Index: 827965 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0585. Min Act: -0.0002

Data Index: 72258 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0590. Min Act: -0.0002

Data Index: 48353 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0579. Min Act: -0.0002

Data Index: 786046 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0597. Min Act: -0.0003

Data Index: 365708 (C4 (Web Text))

Max Activating Token Index: 444