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

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

Neuron 661 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: 3.1380. Min Range: -3.1380

Max Act: 3.0201. Min Act: -0.0000

Data Index: 239311 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.9913. Min Act: -0.0000

Data Index: 361037 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 3.1380. Min Range: -3.1380

Max Act: 3.1380. Min Act: -0.0000

Data Index: 985068 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.7148. Min Act: -0.0000

Data Index: 384699 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.4774. Min Act: -0.0000

Data Index: 310331 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.4253. Min Act: -0.0000

Data Index: 308238 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.4245. Min Act: -0.0000

Data Index: 250528 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.3575. Min Act: -0.0000

Data Index: 2792 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.3784. Min Act: -0.0000

Data Index: 291527 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.1401. Min Act: -0.0000

Data Index: 213789 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.0717. Min Act: -0.0000

Data Index: 574160 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.1247. Min Act: -0.0000

Data Index: 862699 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.0077. Min Act: -0.0000

Data Index: 467625 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.1170. Min Act: -0.0000

Data Index: 432305 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 3.1380. Min Range: -3.1380

Max Act: 2.0362. Min Act: -0.0000

Data Index: 1332411 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 3.1380. Min Range: -3.1380

Max Act: 1.8962. Min Act: -0.0000

Data Index: 978129 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 3.1380. Min Range: -3.1380

Max Act: 1.8500. Min Act: -0.0000

Data Index: 85529 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 3.1380. Min Range: -3.1380

Max Act: 1.8345. Min Act: -0.0000

Data Index: 322137 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 3.1380. Min Range: -3.1380

Max Act: 1.8354. Min Act: -0.0000

Data Index: 995644 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 3.1380. Min Range: -3.1380

Max Act: 1.7279. Min Act: -0.0000

Data Index: 842413 (C4 (Web Text))

Max Activating Token Index: 6