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

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

Neuron 950 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: 0.0739. Min Range: -0.0739

Max Act: 0.0739. Min Act: -0.0003

Data Index: 111285 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0659. Min Act: -0.0003

Data Index: 900943 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0678. Min Act: -0.0003

Data Index: 178425 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0668. Min Act: -0.0003

Data Index: 220320 (C4 (Web Text))

Max Activating Token Index: 248

Text #4

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0656. Min Act: -0.0003

Data Index: 444019 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0645. Min Act: -0.0003

Data Index: 708583 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0656. Min Act: -0.0002

Data Index: 465992 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0636. Min Act: -0.0003

Data Index: 664788 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0623. Min Act: -0.0003

Data Index: 129162 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1175487 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0608. Min Act: -0.0003

Data Index: 282131 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0630. Min Act: -0.0003

Data Index: 95223 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1203292 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0596. Min Act: -0.0002

Data Index: 126477 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0603. Min Act: -0.0003

Data Index: 682152 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0578. Min Act: -0.0003

Data Index: 340192 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0594. Min Act: -0.0002

Data Index: 159571 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0589. Min Act: -0.0003

Data Index: 1144534 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0582. Min Act: -0.0003

Data Index: 890491 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0579. Min Act: -0.0003

Data Index: 1004609 (C4 (Web Text))

Max Activating Token Index: 427