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

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

Neuron 307 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: 1.7233. Min Range: -1.7233

Max Act: 1.7233. Min Act: -0.0000

Data Index: 745121 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.5583. Min Act: -0.0000

Data Index: 624041 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.5315. Min Act: -0.0000

Data Index: 739082 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.3916. Min Act: -0.0000

Data Index: 1360538 (Python Code)

Max Activating Token Index: 830

Text #4

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.5822. Min Act: -0.0000

Data Index: 621022 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.3977. Min Act: -0.0000

Data Index: 1329819 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.3377. Min Act: -0.0000

Data Index: 134404 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.4293. Min Act: -0.0000

Data Index: 524804 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.3781. Min Act: -0.0001

Data Index: 484142 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.4401. Min Act: -0.0000

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.4021. Min Act: -0.0001

Data Index: 292018 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.4077. Min Act: -0.0000

Data Index: 283640 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.4872. Min Act: -0.0000

Data Index: 429894 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.4265. Min Act: -0.0000

Data Index: 144784 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.3531. Min Act: -0.0000

Data Index: 1304205 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.3780. Min Act: -0.0000

Data Index: 234313 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.3721. Min Act: -0.0001

Data Index: 549803 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.3255. Min Act: -0.0000

Data Index: 1642778 (Python Code)

Max Activating Token Index: 923

Text #18

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.3220. Min Act: -0.0000

Data Index: 1189323 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 1.7233. Min Range: -1.7233

Max Act: 1.3687. Min Act: -0.0000

Data Index: 1530370 (Python Code)

Max Activating Token Index: 636