Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 43 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4610. Min Range: -1.4610

Max Act: 1.4610. Min Act: -0.0001

Data Index: 1237770 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 1.4610. Min Range: -1.4610

Max Act: 1.1928. Min Act: -0.0001

Data Index: 831621 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 1.4610. Min Range: -1.4610

Max Act: 1.1787. Min Act: -0.0001

Data Index: 951169 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 1.4610. Min Range: -1.4610

Max Act: 0.9986. Min Act: -0.0001

Data Index: 928328 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 1.4610. Min Range: -1.4610

Max Act: 1.0856. Min Act: -0.0001

Data Index: 1210013 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 1.4610. Min Range: -1.4610

Max Act: 1.0926. Min Act: -0.0001

Data Index: 575685 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 1.4610. Min Range: -1.4610

Max Act: 1.1373. Min Act: -0.0001

Data Index: 1123010 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 1.4610. Min Range: -1.4610

Max Act: 1.0737. Min Act: -0.0001

Data Index: 897354 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 1.4610. Min Range: -1.4610

Max Act: 1.0113. Min Act: -0.0001

Data Index: 1213839 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 1.4610. Min Range: -1.4610

Max Act: 1.1334. Min Act: -0.0001

Data Index: 184560 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 1.4610. Min Range: -1.4610

Max Act: 1.0508. Min Act: -0.0001

Data Index: 300813 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 1.4610. Min Range: -1.4610

Max Act: 1.0317. Min Act: -0.0001

Data Index: 10878 (C4 (Web Text))

Max Activating Token Index: 279

Text #12

Max Range: 1.4610. Min Range: -1.4610

Max Act: 1.0249. Min Act: -0.0001

Data Index: 118829 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 1.4610. Min Range: -1.4610

Max Act: 0.9275. Min Act: -0.0001

Data Index: 188146 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 1.4610. Min Range: -1.4610

Max Act: 0.9840. Min Act: -0.0001

Data Index: 455965 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 1.4610. Min Range: -1.4610

Max Act: 1.0098. Min Act: -0.0001

Data Index: 526746 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 1.4610. Min Range: -1.4610

Max Act: 0.9097. Min Act: -0.0001

Data Index: 1191455 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 1.4610. Min Range: -1.4610

Max Act: 1.0499. Min Act: -0.0001

Data Index: 1246715 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 1.4610. Min Range: -1.4610

Max Act: 1.0161. Min Act: -0.0001

Data Index: 725122 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 1.4610. Min Range: -1.4610

Max Act: 0.9785. Min Act: -0.0001

Data Index: 806662 (C4 (Web Text))

Max Activating Token Index: 546