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

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

Neuron 1535 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0693. Min Act: -0.0005

Data Index: 1239850 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0656. Min Act: -0.0005

Data Index: 824276 (C4 (Web Text))

Max Activating Token Index: 557

Text #2

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0613. Min Act: -0.0005

Data Index: 959975 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0680. Min Act: -0.0005

Data Index: 151853 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0602. Min Act: -0.0005

Data Index: 1178271 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0639. Min Act: -0.0005

Data Index: 533016 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0636. Min Act: -0.0005

Data Index: 1581917 (Python Code)

Max Activating Token Index: 44

Text #7

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0629. Min Act: -0.0005

Data Index: 712553 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0631. Min Act: -0.0005

Data Index: 1174378 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0626. Min Act: -0.0005

Data Index: 1008349 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0596. Min Act: -0.0005

Data Index: 529986 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0638. Min Act: -0.0005

Data Index: 648213 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0613. Min Act: -0.0005

Data Index: 13473 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0603. Min Act: -0.0005

Data Index: 878720 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0604. Min Act: -0.0005

Data Index: 991535 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0633. Min Act: -0.0005

Data Index: 402630 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0591. Min Act: -0.0005

Data Index: 23379 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0594. Min Act: -0.0005

Data Index: 889829 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0592. Min Act: -0.0005

Data Index: 131955 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.0693. Min Range: -0.0693

Max Act: 0.0592. Min Act: -0.0005

Data Index: 470964 (C4 (Web Text))

Max Activating Token Index: 710