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

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

Neuron 838 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.2607. Min Act: -0.0000

Data Index: 400553 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.2509. Min Act: -0.0000

Data Index: 739564 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.1253. Min Act: -0.0000

Data Index: 670490 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.1052. Min Act: -0.0000

Data Index: 1054537 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.0171. Min Act: -0.0000

Data Index: 987883 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.0757. Min Act: -0.0000

Data Index: 1112161 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.0378. Min Act: -0.0000

Data Index: 500541 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1124053 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.0244. Min Act: 0.0000

Data Index: 176405 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.0266. Min Act: -0.0000

Data Index: 259666 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 1.2607. Min Range: -1.2607

Max Act: 1.0116. Min Act: -0.0000

Data Index: 611642 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 1.2607. Min Range: -1.2607

Max Act: 0.9601. Min Act: -0.0000

Data Index: 652519 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 1.2607. Min Range: -1.2607

Max Act: 0.9500. Min Act: -0.0000

Data Index: 1124715 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 1.2607. Min Range: -1.2607

Max Act: 0.9447. Min Act: -0.0000

Data Index: 459208 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 1.2607. Min Range: -1.2607

Max Act: 0.9257. Min Act: -0.0000

Data Index: 459517 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 1.2607. Min Range: -1.2607

Max Act: 0.9029. Min Act: -0.0000

Data Index: 1011638 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 1.2607. Min Range: -1.2607

Max Act: 0.8750. Min Act: -0.0000

Data Index: 100611 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 1.2607. Min Range: -1.2607

Max Act: 0.8403. Min Act: -0.0000

Data Index: 684807 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 1.2607. Min Range: -1.2607

Max Act: 0.8535. Min Act: -0.0000

Data Index: 582062 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 1.2607. Min Range: -1.2607

Max Act: 0.8491. Min Act: -0.0000

Data Index: 557883 (C4 (Web Text))

Max Activating Token Index: 1020