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

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

Neuron 4227 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3282. Min Range: -4.3282

Max Act: 4.3282. Min Act: -0.0000

Data Index: 152650 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 4.3282. Min Range: -4.3282

Max Act: 3.1839. Min Act: -0.0000

Data Index: 1112769 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.7106. Min Act: -0.0000

Data Index: 696002 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.6803. Min Act: -0.0000

Data Index: 518406 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.4744. Min Act: -0.0000

Data Index: 1282905 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.5952. Min Act: -0.0000

Data Index: 1177839 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.4851. Min Act: -0.0000

Data Index: 761728 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.5082. Min Act: -0.0000

Data Index: 1352188 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.4701. Min Act: -0.0000

Data Index: 1151467 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.4501. Min Act: -0.0000

Data Index: 785425 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.4269. Min Act: -0.0000

Data Index: 1006265 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.2908. Min Act: -0.0000

Data Index: 306232 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.5017. Min Act: -0.0000

Data Index: 964091 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.2454. Min Act: -0.0000

Data Index: 302184 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.3195. Min Act: -0.0000

Data Index: 1341267 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.3390. Min Act: -0.0000

Data Index: 68584 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.3031. Min Act: -0.0000

Data Index: 871661 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.2896. Min Act: -0.0000

Data Index: 1206001 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.4199. Min Act: -0.0000

Data Index: 98247 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 4.3282. Min Range: -4.3282

Max Act: 2.2918. Min Act: -0.0000

Data Index: 1266587 (C4 (Web Text))

Max Activating Token Index: 454