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

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

Neuron 3891 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1187. Min Range: -5.1187

Max Act: 5.1187. Min Act: -0.0000

Data Index: 1285877 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 5.1187. Min Range: -5.1187

Max Act: 4.5938. Min Act: -0.0000

Data Index: 961868 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 5.1187. Min Range: -5.1187

Max Act: 4.4975. Min Act: -0.0000

Data Index: 788614 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 5.1187. Min Range: -5.1187

Max Act: 4.6406. Min Act: -0.0000

Data Index: 38368 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 5.1187. Min Range: -5.1187

Max Act: 4.2899. Min Act: -0.0000

Data Index: 386497 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 5.1187. Min Range: -5.1187

Max Act: 4.0822. Min Act: -0.0000

Data Index: 330162 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 5.1187. Min Range: -5.1187

Max Act: 3.9317. Min Act: -0.0000

Data Index: 665001 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 5.1187. Min Range: -5.1187

Max Act: 4.0807. Min Act: -0.0000

Data Index: 528085 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 5.1187. Min Range: -5.1187

Max Act: 4.0099. Min Act: -0.0000

Data Index: 522294 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 5.1187. Min Range: -5.1187

Max Act: 4.0173. Min Act: -0.0000

Data Index: 479500 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 5.1187. Min Range: -5.1187

Max Act: 3.9189. Min Act: -0.0000

Data Index: 1234790 (C4 (Web Text))

Max Activating Token Index: 708

Text #11

Max Range: 5.1187. Min Range: -5.1187

Max Act: 4.0787. Min Act: -0.0000

Data Index: 106664 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 5.1187. Min Range: -5.1187

Max Act: 3.8741. Min Act: -0.0000

Data Index: 914096 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 5.1187. Min Range: -5.1187

Max Act: 3.9751. Min Act: -0.0000

Data Index: 688917 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 5.1187. Min Range: -5.1187

Max Act: 3.5864. Min Act: -0.0000

Data Index: 677476 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 5.1187. Min Range: -5.1187

Max Act: 3.7255. Min Act: -0.0000

Data Index: 1040534 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 5.1187. Min Range: -5.1187

Max Act: 3.7172. Min Act: -0.0000

Data Index: 1096049 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 5.1187. Min Range: -5.1187

Max Act: 3.6979. Min Act: -0.0000

Data Index: 214962 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 5.1187. Min Range: -5.1187

Max Act: 3.6854. Min Act: -0.0000

Data Index: 281933 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 5.1187. Min Range: -5.1187

Max Act: 3.5076. Min Act: -0.0000

Data Index: 488009 (C4 (Web Text))

Max Activating Token Index: 214