Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 243 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.4640. Min Act: -0.0000

Data Index: 816424 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.4850. Min Act: -0.0000

Data Index: 286761 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.3892. Min Act: -0.0000

Data Index: 255702 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.3153. Min Act: -0.0000

Data Index: 478795 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1653. Min Act: -0.0000

Data Index: 539592 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1169. Min Act: -0.0000

Data Index: 879981 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1131. Min Act: -0.0000

Data Index: 92534 (C4 (Web Text))

Max Activating Token Index: 857

Text #7

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1187. Min Act: -0.0000

Data Index: 998948 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.1148. Min Act: -0.0000

Data Index: 824316 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.0865. Min Act: -0.0000

Data Index: 207703 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.0080. Min Act: -0.0000

Data Index: 476413 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1322047 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.0853. Min Act: -0.0000

Data Index: 1353003 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.0792. Min Act: -0.0000

Data Index: 485261 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 1.4850. Min Range: -1.4850

Max Act: 1.0064. Min Act: -0.0000

Data Index: 841779 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 1.4850. Min Range: -1.4850

Max Act: 0.9991. Min Act: -0.0000

Data Index: 131717 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 1.4850. Min Range: -1.4850

Max Act: 0.9377. Min Act: -0.0000

Data Index: 589918 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 1.4850. Min Range: -1.4850

Max Act: 0.9732. Min Act: -0.0000

Data Index: 1257839 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 1.4850. Min Range: -1.4850

Max Act: 0.9682. Min Act: -0.0000

Data Index: 577896 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 1.4850. Min Range: -1.4850

Max Act: 0.8880. Min Act: -0.0000

Data Index: 663402 (C4 (Web Text))

Max Activating Token Index: 136