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

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

Neuron 971 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: 0.0732. Min Range: -0.0732

Max Act: 0.0732. Min Act: -0.0003

Data Index: 1320685 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0719. Min Act: -0.0003

Data Index: 378329 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0709. Min Act: -0.0003

Data Index: 414122 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0615. Min Act: -0.0003

Data Index: 794588 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0665. Min Act: -0.0003

Data Index: 215393 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0658. Min Act: -0.0003

Data Index: 412818 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0629. Min Act: -0.0003

Data Index: 1288647 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0624. Min Act: -0.0003

Data Index: 70672 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0610. Min Act: -0.0003

Data Index: 428417 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0601. Min Act: -0.0003

Data Index: 910743 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0614. Min Act: -0.0003

Data Index: 391572 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1035030 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0628. Min Act: -0.0003

Data Index: 472631 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0633. Min Act: -0.0003

Data Index: 678190 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0598. Min Act: -0.0003

Data Index: 177029 (C4 (Web Text))

Max Activating Token Index: 340

Text #15

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0591. Min Act: -0.0003

Data Index: 216789 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1207944 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0560. Min Act: -0.0003

Data Index: 193291 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0583. Min Act: -0.0003

Data Index: 818607 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 0.0732. Min Range: -0.0732

Max Act: 0.0581. Min Act: -0.0003

Data Index: 821360 (C4 (Web Text))

Max Activating Token Index: 664