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

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

Neuron 2625 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1728. Min Range: -4.1728

Max Act: 4.1728. Min Act: -0.0000

Data Index: 16058 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 4.1728. Min Range: -4.1728

Max Act: 3.6092. Min Act: -0.0000

Data Index: 715161 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 4.1728. Min Range: -4.1728

Max Act: 3.4096. Min Act: -0.0001

Data Index: 587623 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 4.1728. Min Range: -4.1728

Max Act: 3.0827. Min Act: -0.0000

Data Index: 1199719 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.6193. Min Act: -0.0000

Data Index: 1101649 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.6563. Min Act: -0.0000

Data Index: 919387 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.6197. Min Act: -0.0000

Data Index: 34653 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.5981. Min Act: -0.0000

Data Index: 549664 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.3101. Min Act: -0.0000

Data Index: 635389 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.5344. Min Act: -0.0000

Data Index: 646540 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.6010. Min Act: -0.0000

Data Index: 572364 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.5724. Min Act: -0.0000

Data Index: 1296810 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.2212. Min Act: -0.0000

Data Index: 304206 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.5890. Min Act: -0.0000

Data Index: 21080 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.4786. Min Act: -0.0000

Data Index: 1204100 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.3506. Min Act: -0.0000

Data Index: 605604 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.4237. Min Act: -0.0000

Data Index: 346400 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.3249. Min Act: -0.0000

Data Index: 557119 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.2167. Min Act: -0.0000

Data Index: 1097192 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 4.1728. Min Range: -4.1728

Max Act: 2.3098. Min Act: -0.0000

Data Index: 977895 (C4 (Web Text))

Max Activating Token Index: 895