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

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

Neuron 3823 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.9620. Min Act: -0.0000

Data Index: 1320358 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 1.0184. Min Range: -1.0184

Max Act: 1.0184. Min Act: 0.0000

Data Index: 436948 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.9280. Min Act: -0.0000

Data Index: 812018 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.9212. Min Act: -0.0000

Data Index: 1123527 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.8642. Min Act: 0.0001

Data Index: 36165 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.8295. Min Act: 0.0000

Data Index: 812013 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.8072. Min Act: 0.0000

Data Index: 73332 (C4 (Web Text))

Max Activating Token Index: 605

Text #7

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7456. Min Act: -0.0000

Data Index: 956776 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7790. Min Act: -0.0000

Data Index: 576838 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1097119 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1254817 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7511. Min Act: -0.0000

Data Index: 645849 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7500. Min Act: -0.0000

Data Index: 888723 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1218488 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7454. Min Act: -0.0000

Data Index: 1152348 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7333. Min Act: -0.0000

Data Index: 978134 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7144. Min Act: -0.0000

Data Index: 688014 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.6853. Min Act: 0.0000

Data Index: 483215 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1128244 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7238. Min Act: 0.0000

Data Index: 1119843 (C4 (Web Text))

Max Activating Token Index: 179