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

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

Neuron 1046 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.7262. Min Act: -0.0000

Data Index: 942807 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.7053. Min Act: -0.0000

Data Index: 517344 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.5319. Min Act: -0.0000

Data Index: 14146 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.5152. Min Act: -0.0000

Data Index: 653406 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.5030. Min Act: -0.0000

Data Index: 570722 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.3969. Min Act: -0.0000

Data Index: 1081541 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.4361. Min Act: -0.0000

Data Index: 1352263 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.4130. Min Act: -0.0000

Data Index: 1338415 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.3748. Min Act: -0.0000

Data Index: 919375 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.2347. Min Act: -0.0000

Data Index: 526920 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.2998. Min Act: -0.0000

Data Index: 148831 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.2475. Min Act: -0.0000

Data Index: 109179 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.2219. Min Act: -0.0000

Data Index: 520243 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.2264. Min Act: -0.0000

Data Index: 790935 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.1800. Min Act: -0.0000

Data Index: 1338005 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.1756. Min Act: -0.0000

Data Index: 508454 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.2407. Min Act: -0.0000

Data Index: 1165340 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.1495. Min Act: -0.0000

Data Index: 228099 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.0635. Min Act: -0.0000

Data Index: 341067 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 1.7262. Min Range: -1.7262

Max Act: 1.0929. Min Act: -0.0000

Data Index: 968320 (C4 (Web Text))

Max Activating Token Index: 150