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

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

Neuron 1849 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6267. Min Range: -3.6267

Max Act: 3.6267. Min Act: -0.0000

Data Index: 687024 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 3.6267. Min Range: -3.6267

Max Act: 3.1713. Min Act: -0.0000

Data Index: 71256 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 3.6267. Min Range: -3.6267

Max Act: 3.2586. Min Act: -0.0000

Data Index: 833257 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 3.6267. Min Range: -3.6267

Max Act: 2.7713. Min Act: -0.0000

Data Index: 608033 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 3.6267. Min Range: -3.6267

Max Act: 3.0288. Min Act: -0.0000

Data Index: 473510 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 3.6267. Min Range: -3.6267

Max Act: 3.0252. Min Act: -0.0000

Data Index: 1288223 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 3.6267. Min Range: -3.6267

Max Act: 2.9929. Min Act: -0.0000

Data Index: 386370 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 3.6267. Min Range: -3.6267

Max Act: 2.9699. Min Act: -0.0000

Data Index: 919722 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 3.6267. Min Range: -3.6267

Max Act: 3.0887. Min Act: -0.0000

Data Index: 878774 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 3.6267. Min Range: -3.6267

Max Act: 2.7421. Min Act: -0.0000

Data Index: 150485 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 3.6267. Min Range: -3.6267

Max Act: 2.8730. Min Act: -0.0000

Data Index: 136299 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 3.6267. Min Range: -3.6267

Max Act: 2.8258. Min Act: -0.0000

Data Index: 661080 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 3.6267. Min Range: -3.6267

Max Act: 2.6790. Min Act: -0.0000

Data Index: 332107 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 3.6267. Min Range: -3.6267

Max Act: 2.7687. Min Act: -0.0000

Data Index: 1165959 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 3.6267. Min Range: -3.6267

Max Act: 2.6995. Min Act: -0.0000

Data Index: 242547 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 3.6267. Min Range: -3.6267

Max Act: 2.6853. Min Act: -0.0000

Data Index: 79151 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 3.6267. Min Range: -3.6267

Max Act: 2.6627. Min Act: -0.0000

Data Index: 283120 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 3.6267. Min Range: -3.6267

Max Act: 2.8575. Min Act: -0.0000

Data Index: 43445 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 3.6267. Min Range: -3.6267

Max Act: 2.6222. Min Act: -0.0000

Data Index: 544723 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 3.6267. Min Range: -3.6267

Max Act: 2.5808. Min Act: -0.0000

Data Index: 800262 (C4 (Web Text))

Max Activating Token Index: 224