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

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

Neuron 2344 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: 2.1828. Min Range: -2.1828

Max Act: 2.1828. Min Act: -0.0000

Data Index: 1104219 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 2.1828. Min Range: -2.1828

Max Act: 2.0217. Min Act: -0.0000

Data Index: 510376 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.6871. Min Act: -0.0000

Data Index: 1051660 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.4859. Min Act: -0.0000

Data Index: 54650 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.4139. Min Act: -0.0000

Data Index: 418137 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.3835. Min Act: -0.0000

Data Index: 1170249 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.3119. Min Act: -0.0000

Data Index: 1358000 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.3622. Min Act: -0.0000

Data Index: 721340 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.2061. Min Act: -0.0000

Data Index: 196481 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.2571. Min Act: -0.0000

Data Index: 217643 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.2535. Min Act: -0.0000

Data Index: 982613 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.2518. Min Act: -0.0000

Data Index: 554676 (C4 (Web Text))

Max Activating Token Index: 710

Text #12

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.2391. Min Act: -0.0000

Data Index: 987483 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.1524. Min Act: -0.0000

Data Index: 640750 (C4 (Web Text))

Max Activating Token Index: 855

Text #14

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.1461. Min Act: -0.0000

Data Index: 417443 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.1903. Min Act: -0.0000

Data Index: 640357 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.1158. Min Act: -0.0000

Data Index: 1286076 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.2078. Min Act: -0.0000

Data Index: 694130 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.1672. Min Act: -0.0000

Data Index: 152688 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 2.1828. Min Range: -2.1828

Max Act: 1.1277. Min Act: -0.0000

Data Index: 1291670 (C4 (Web Text))

Max Activating Token Index: 962