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

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

Neuron 718 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: 2.6295. Min Range: -2.6295

Max Act: 2.6295. Min Act: -0.0000

Data Index: 491814 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.4000. Min Act: -0.0000

Data Index: 744142 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.1384. Min Act: -0.0000

Data Index: 43378 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.1270. Min Act: -0.0000

Data Index: 863654 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.2357. Min Act: -0.0000

Data Index: 432293 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.2012. Min Act: -0.0000

Data Index: 830668 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.1996. Min Act: -0.0000

Data Index: 674580 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.0790. Min Act: -0.0000

Data Index: 29571 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.2461. Min Act: -0.0000

Data Index: 982542 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.1590. Min Act: -0.0000

Data Index: 642856 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.0257. Min Act: -0.0000

Data Index: 481456 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.0232. Min Act: -0.0000

Data Index: 814328 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.0017. Min Act: -0.0000

Data Index: 626324 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.2218. Min Act: -0.0000

Data Index: 223852 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.2013. Min Act: -0.0000

Data Index: 447895 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.0905. Min Act: -0.0000

Data Index: 1030213 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 2.6295. Min Range: -2.6295

Max Act: 1.8800. Min Act: -0.0000

Data Index: 551932 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.0522. Min Act: -0.0000

Data Index: 122053 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.0623. Min Act: -0.0000

Data Index: 413808 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 2.6295. Min Range: -2.6295

Max Act: 2.0533. Min Act: -0.0000

Data Index: 1166276 (C4 (Web Text))

Max Activating Token Index: 683