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

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

Neuron 35 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1105864 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.3588. Min Act: -0.0000

Data Index: 975697 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.3481. Min Act: -0.0000

Data Index: 569937 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.3284. Min Act: -0.0000

Data Index: 333213 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2880. Min Act: -0.0000

Data Index: 508466 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2759. Min Act: -0.0000

Data Index: 1267070 (C4 (Web Text))

Max Activating Token Index: 854

Text #6

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2733. Min Act: -0.0000

Data Index: 325470 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2862. Min Act: -0.0000

Data Index: 1122934 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2701. Min Act: -0.0000

Data Index: 469657 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2759. Min Act: -0.0000

Data Index: 1198561 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2633. Min Act: -0.0000

Data Index: 847558 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2706. Min Act: -0.0000

Data Index: 607701 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2776. Min Act: -0.0000

Data Index: 1046119 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2760. Min Act: -0.0000

Data Index: 534184 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2634. Min Act: -0.0000

Data Index: 777338 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2601. Min Act: -0.0000

Data Index: 61375 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2528. Min Act: -0.0000

Data Index: 1186653 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2554. Min Act: -0.0000

Data Index: 554391 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1323679 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.3888. Min Range: -0.3888

Max Act: 0.2526. Min Act: -0.0000

Data Index: 612454 (C4 (Web Text))

Max Activating Token Index: 245