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

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

Neuron 2538 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3040. Min Range: -1.3040

Max Act: 1.3040. Min Act: -0.0001

Data Index: 403947 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 1.3040. Min Range: -1.3040

Max Act: 1.2391. Min Act: -0.0001

Data Index: 345175 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 1.3040. Min Range: -1.3040

Max Act: 1.0394. Min Act: -0.0000

Data Index: 819619 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 1.3040. Min Range: -1.3040

Max Act: 1.1119. Min Act: -0.0001

Data Index: 226845 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 1.3040. Min Range: -1.3040

Max Act: 1.1359. Min Act: -0.0000

Data Index: 551858 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 1.3040. Min Range: -1.3040

Max Act: 1.0299. Min Act: -0.0001

Data Index: 661692 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.9659. Min Act: -0.0000

Data Index: 234141 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 1.3040. Min Range: -1.3040

Max Act: 1.0272. Min Act: -0.0000

Data Index: 386779 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.9799. Min Act: -0.0001

Data Index: 566393 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.9522. Min Act: -0.0000

Data Index: 667344 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 1.3040. Min Range: -1.3040

Max Act: 1.0807. Min Act: -0.0001

Data Index: 574834 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.9353. Min Act: -0.0001

Data Index: 728815 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.9052. Min Act: -0.0001

Data Index: 1221695 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.9387. Min Act: -0.0001

Data Index: 1168435 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.9123. Min Act: -0.0001

Data Index: 62790 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.8613. Min Act: -0.0000

Data Index: 1251433 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.9313. Min Act: -0.0001

Data Index: 1090023 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.8875. Min Act: -0.0001

Data Index: 151153 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.9923. Min Act: -0.0001

Data Index: 269964 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 1.3040. Min Range: -1.3040

Max Act: 0.9068. Min Act: -0.0001

Data Index: 1301237 (C4 (Web Text))

Max Activating Token Index: 71