Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 688 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0516. Min Act: -0.0003

Data Index: 788617 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0547. Min Act: -0.0003

Data Index: 88026 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0652. Min Act: -0.0003

Data Index: 520337 (C4 (Web Text))

Max Activating Token Index: 360

Text #3

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0601. Min Act: -0.0003

Data Index: 1187554 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0556. Min Act: -0.0003

Data Index: 896770 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0574. Min Act: -0.0003

Data Index: 1257488 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0618. Min Act: -0.0003

Data Index: 1283504 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0594. Min Act: -0.0004

Data Index: 163391 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0611. Min Act: -0.0003

Data Index: 215317 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0588. Min Act: -0.0003

Data Index: 1279112 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0603. Min Act: -0.0003

Data Index: 54986 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0513. Min Act: -0.0003

Data Index: 380175 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0556. Min Act: -0.0003

Data Index: 267602 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1235459 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0557. Min Act: -0.0003

Data Index: 684975 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0575. Min Act: -0.0003

Data Index: 141487 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1128361 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1236110 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0591. Min Act: -0.0003

Data Index: 686794 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.0652. Min Range: -0.0652

Max Act: 0.0591. Min Act: -0.0003

Data Index: 942658 (C4 (Web Text))

Max Activating Token Index: 361