Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1483 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.6646. Min Act: -0.0000

Data Index: 1329990 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.5613. Min Act: -0.0000

Data Index: 594013 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1039162 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1136576 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4598. Min Act: -0.0000

Data Index: 626565 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1070349 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1191507 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4573. Min Act: -0.0000

Data Index: 1287842 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4462. Min Act: -0.0000

Data Index: 42898 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4525. Min Act: -0.0000

Data Index: 530530 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4231. Min Act: -0.0000

Data Index: 828045 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4580. Min Act: -0.0000

Data Index: 586985 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4477. Min Act: -0.0000

Data Index: 168488 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4314. Min Act: -0.0000

Data Index: 376910 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4089. Min Act: -0.0000

Data Index: 10249 (C4 (Web Text))

Max Activating Token Index: 472

Text #15

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4000. Min Act: -0.0000

Data Index: 16109 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1335301 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4108. Min Act: -0.0000

Data Index: 919082 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4234. Min Act: -0.0000

Data Index: 964995 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.6646. Min Range: -0.6646

Max Act: 0.4138. Min Act: -0.0000

Data Index: 751109 (C4 (Web Text))

Max Activating Token Index: 865