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

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

Neuron 3651 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.8313. Min Act: -0.0001

Data Index: 766827 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.6265. Min Act: -0.0001

Data Index: 693797 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.4401. Min Act: -0.0001

Data Index: 602273 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.5920. Min Act: -0.0001

Data Index: 632098 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.5483. Min Act: -0.0001

Data Index: 387015 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.5222. Min Act: -0.0001

Data Index: 1064853 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.4588. Min Act: -0.0001

Data Index: 404034 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.2871. Min Act: -0.0001

Data Index: 1137671 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.7818. Min Act: -0.0001

Data Index: 588604 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.4190. Min Act: -0.0001

Data Index: 112153 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.6026. Min Act: -0.0001

Data Index: 378825 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.0202. Min Act: -0.0001

Data Index: 17848 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.5178. Min Act: -0.0001

Data Index: 251770 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.3314. Min Act: -0.0001

Data Index: 814907 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.1311. Min Act: -0.0001

Data Index: 733412 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.1315. Min Act: -0.0001

Data Index: 1192749 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.1066. Min Act: -0.0001

Data Index: 37195 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.1044. Min Act: -0.0001

Data Index: 919616 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.4318. Min Act: -0.0001

Data Index: 440980 (C4 (Web Text))

Max Activating Token Index: 742

Text #19

Max Range: 6.8313. Min Range: -6.8313

Max Act: 6.2330. Min Act: -0.0001

Data Index: 515748 (C4 (Web Text))

Max Activating Token Index: 641