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

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

Neuron 1717 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0789. Min Range: -3.0789

Max Act: 3.0789. Min Act: -0.0000

Data Index: 8052 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.8523. Min Act: -0.0000

Data Index: 869311 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 3.0789. Min Range: -3.0789

Max Act: 3.0304. Min Act: -0.0000

Data Index: 808502 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.6869. Min Act: -0.0000

Data Index: 1056308 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.7092. Min Act: -0.0001

Data Index: 317531 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.6568. Min Act: -0.0000

Data Index: 613960 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.3303. Min Act: -0.0000

Data Index: 710583 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.4460. Min Act: -0.0000

Data Index: 711808 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.5093. Min Act: -0.0000

Data Index: 1326345 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.4979. Min Act: -0.0000

Data Index: 863205 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.5048. Min Act: -0.0000

Data Index: 639695 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.4830. Min Act: -0.0000

Data Index: 90481 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.3287. Min Act: -0.0000

Data Index: 1229966 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.4422. Min Act: -0.0000

Data Index: 557650 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.4291. Min Act: -0.0000

Data Index: 629500 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.5479. Min Act: -0.0000

Data Index: 799447 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.4045. Min Act: -0.0000

Data Index: 1209965 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.3954. Min Act: -0.0000

Data Index: 927740 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.2882. Min Act: -0.0000

Data Index: 744041 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 3.0789. Min Range: -3.0789

Max Act: 2.2569. Min Act: -0.0000

Data Index: 1345772 (C4 (Web Text))

Max Activating Token Index: 229