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

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

Neuron 260 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1154441 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0792. Min Act: -0.0002

Data Index: 205524 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0816. Min Act: -0.0002

Data Index: 979257 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0764. Min Act: -0.0002

Data Index: 362817 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0759. Min Act: -0.0002

Data Index: 963065 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0778. Min Act: -0.0002

Data Index: 475913 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0820. Min Act: -0.0002

Data Index: 153305 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0708. Min Act: -0.0002

Data Index: 532719 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0730. Min Act: -0.0002

Data Index: 697875 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1352408 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0730. Min Act: -0.0002

Data Index: 282063 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1335433 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0719. Min Act: -0.0002

Data Index: 904640 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1026205 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0724. Min Act: -0.0002

Data Index: 946133 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0725. Min Act: -0.0002

Data Index: 687237 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0689. Min Act: -0.0002

Data Index: 305543 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1253837 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1127380 (C4 (Web Text))

Max Activating Token Index: 565

Text #19

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0693. Min Act: -0.0002

Data Index: 213396 (C4 (Web Text))

Max Activating Token Index: 937