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

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

Neuron 5356 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.5712. Min Range: -8.5712

Max Act: 8.2740. Min Act: -0.0000

Data Index: 1251127 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 8.5712. Min Range: -8.5712

Max Act: 8.2269. Min Act: -0.0000

Data Index: 912001 (C4 (Web Text))

Max Activating Token Index: 113

Text #2

Max Range: 8.5712. Min Range: -8.5712

Max Act: 8.0468. Min Act: -0.0000

Data Index: 883716 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 8.5712. Min Range: -8.5712

Max Act: 8.5712. Min Act: -0.0000

Data Index: 738869 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 8.5712. Min Range: -8.5712

Max Act: 8.1923. Min Act: -0.0000

Data Index: 935352 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 8.5712. Min Range: -8.5712

Max Act: 8.1758. Min Act: -0.0000

Data Index: 307852 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 8.5712. Min Range: -8.5712

Max Act: 7.9767. Min Act: -0.0000

Data Index: 769 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 8.5712. Min Range: -8.5712

Max Act: 7.8239. Min Act: -0.0000

Data Index: 53409 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 8.5712. Min Range: -8.5712

Max Act: 7.6606. Min Act: -0.0000

Data Index: 296903 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 8.5712. Min Range: -8.5712

Max Act: 8.0214. Min Act: -0.0000

Data Index: 657578 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 8.5712. Min Range: -8.5712

Max Act: 7.4343. Min Act: -0.0000

Data Index: 220280 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 8.5712. Min Range: -8.5712

Max Act: 7.7062. Min Act: -0.0000

Data Index: 293616 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 8.5712. Min Range: -8.5712

Max Act: 7.6381. Min Act: -0.0000

Data Index: 685037 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 8.5712. Min Range: -8.5712

Max Act: 7.7912. Min Act: -0.0000

Data Index: 452838 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 8.5712. Min Range: -8.5712

Max Act: 7.4878. Min Act: -0.0000

Data Index: 244284 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 8.5712. Min Range: -8.5712

Max Act: 7.2959. Min Act: -0.0000

Data Index: 901896 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 8.5712. Min Range: -8.5712

Max Act: 7.2194. Min Act: -0.0000

Data Index: 141770 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 8.5712. Min Range: -8.5712

Max Act: 7.3241. Min Act: -0.0000

Data Index: 1256287 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 8.5712. Min Range: -8.5712

Max Act: 7.0761. Min Act: -0.0000

Data Index: 500945 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 8.5712. Min Range: -8.5712

Max Act: 7.1011. Min Act: -0.0000

Data Index: 372682 (C4 (Web Text))

Max Activating Token Index: 753