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

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

Neuron 513 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0846. Min Range: -1.0846

Max Act: 1.0846. Min Act: -0.0000

Data Index: 1143089 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 1.0846. Min Range: -1.0846

Max Act: 1.0130. Min Act: 0.0000

Data Index: 12791 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 1.0846. Min Range: -1.0846

Max Act: 1.0467. Min Act: -0.0000

Data Index: 204106 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.7184. Min Act: -0.0000

Data Index: 188739 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.7896. Min Act: -0.0000

Data Index: 151071 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6790. Min Act: -0.0000

Data Index: 1076302 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.7062. Min Act: -0.0000

Data Index: 426693 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6199. Min Act: -0.0000

Data Index: 77967 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1106988 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6363. Min Act: -0.0000

Data Index: 304208 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6481. Min Act: -0.0000

Data Index: 392757 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1307289 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.7209. Min Act: -0.0000

Data Index: 467402 (C4 (Web Text))

Max Activating Token Index: 264

Text #13

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6749. Min Act: -0.0000

Data Index: 760308 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6538. Min Act: -0.0000

Data Index: 1017093 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6108. Min Act: -0.0000

Data Index: 338749 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.5873. Min Act: -0.0000

Data Index: 826727 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.6122. Min Act: -0.0000

Data Index: 918084 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.5540. Min Act: -0.0000

Data Index: 410576 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 1.0846. Min Range: -1.0846

Max Act: 0.5525. Min Act: 0.0000

Data Index: 1005141 (C4 (Web Text))

Max Activating Token Index: 117