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

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

Neuron 79 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3504. Min Range: -1.3504

Max Act: 1.3504. Min Act: -0.0001

Data Index: 1003053 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 1.3504. Min Range: -1.3504

Max Act: 1.1573. Min Act: -0.0001

Data Index: 1256820 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 1.3504. Min Range: -1.3504

Max Act: 1.1849. Min Act: -0.0001

Data Index: 52660 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.8914. Min Act: -0.0001

Data Index: 588155 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.8898. Min Act: -0.0001

Data Index: 843656 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.8753. Min Act: -0.0001

Data Index: 346017 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.8373. Min Act: -0.0001

Data Index: 472036 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.8580. Min Act: -0.0001

Data Index: 605604 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.8559. Min Act: -0.0001

Data Index: 1053330 (C4 (Web Text))

Max Activating Token Index: 910

Text #9

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.8015. Min Act: -0.0001

Data Index: 89058 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.8130. Min Act: -0.0001

Data Index: 199907 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.7559. Min Act: -0.0001

Data Index: 250630 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.7708. Min Act: -0.0001

Data Index: 430960 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.8025. Min Act: -0.0001

Data Index: 656296 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.7894. Min Act: -0.0001

Data Index: 171272 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.7447. Min Act: -0.0001

Data Index: 1259661 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.7069. Min Act: -0.0001

Data Index: 118584 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.7183. Min Act: -0.0001

Data Index: 1121087 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.6998. Min Act: -0.0001

Data Index: 1098340 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 1.3504. Min Range: -1.3504

Max Act: 0.7081. Min Act: -0.0001

Data Index: 558526 (C4 (Web Text))

Max Activating Token Index: 977