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

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

Neuron 801 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: 7.4132. Min Range: -7.4132

Max Act: 7.4132. Min Act: -0.0000

Data Index: 146839 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 7.4132. Min Range: -7.4132

Max Act: 6.4930. Min Act: -0.0000

Data Index: 647818 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 7.4132. Min Range: -7.4132

Max Act: 6.0334. Min Act: -0.0000

Data Index: 910308 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 7.4132. Min Range: -7.4132

Max Act: 6.3908. Min Act: -0.0000

Data Index: 285168 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 7.4132. Min Range: -7.4132

Max Act: 6.1220. Min Act: -0.0000

Data Index: 379882 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 7.4132. Min Range: -7.4132

Max Act: 6.0775. Min Act: -0.0000

Data Index: 38686 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 7.4132. Min Range: -7.4132

Max Act: 6.3972. Min Act: -0.0000

Data Index: 1356931 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 7.4132. Min Range: -7.4132

Max Act: 5.7791. Min Act: -0.0000

Data Index: 722718 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 7.4132. Min Range: -7.4132

Max Act: 5.9756. Min Act: -0.0000

Data Index: 215649 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 7.4132. Min Range: -7.4132

Max Act: 5.9379. Min Act: -0.0000

Data Index: 335009 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 7.4132. Min Range: -7.4132

Max Act: 5.8471. Min Act: -0.0000

Data Index: 761893 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 7.4132. Min Range: -7.4132

Max Act: 5.6157. Min Act: -0.0000

Data Index: 666290 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 7.4132. Min Range: -7.4132

Max Act: 5.9288. Min Act: -0.0000

Data Index: 413830 (C4 (Web Text))

Max Activating Token Index: 165

Text #13

Max Range: 7.4132. Min Range: -7.4132

Max Act: 5.3479. Min Act: -0.0000

Data Index: 1304060 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 7.4132. Min Range: -7.4132

Max Act: 5.8741. Min Act: -0.0000

Data Index: 618097 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 7.4132. Min Range: -7.4132

Max Act: 5.3087. Min Act: -0.0000

Data Index: 1142652 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 7.4132. Min Range: -7.4132

Max Act: 5.6638. Min Act: -0.0000

Data Index: 784185 (C4 (Web Text))

Max Activating Token Index: 468

Text #17

Max Range: 7.4132. Min Range: -7.4132

Max Act: 6.0332. Min Act: -0.0000

Data Index: 565888 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 7.4132. Min Range: -7.4132

Max Act: 5.5183. Min Act: -0.0000

Data Index: 241441 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 7.4132. Min Range: -7.4132

Max Act: 5.5916. Min Act: -0.0000

Data Index: 621142 (C4 (Web Text))

Max Activating Token Index: 946