Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 923 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0667. Min Act: -0.0003

Data Index: 860327 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0709. Min Act: -0.0003

Data Index: 68292 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0690. Min Act: -0.0003

Data Index: 238164 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0706. Min Act: -0.0003

Data Index: 1046095 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0687. Min Act: -0.0003

Data Index: 181813 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1248828 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1007518 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0710. Min Act: -0.0003

Data Index: 1273793 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0628. Min Act: -0.0003

Data Index: 1312341 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0659. Min Act: -0.0003

Data Index: 877463 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1025012 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0585. Min Act: -0.0003

Data Index: 689719 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0586. Min Act: -0.0003

Data Index: 454241 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0598. Min Act: -0.0003

Data Index: 923788 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0587. Min Act: -0.0003

Data Index: 599769 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0578. Min Act: -0.0003

Data Index: 256637 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0598. Min Act: -0.0003

Data Index: 177645 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0636. Min Act: -0.0003

Data Index: 843409 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0619. Min Act: -0.0003

Data Index: 595377 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0578. Min Act: -0.0003

Data Index: 459224 (C4 (Web Text))

Max Activating Token Index: 899