Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1280 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.7171. Min Act: -0.0001

Data Index: 314725 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.6845. Min Act: -0.0001

Data Index: 1015093 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.3002. Min Act: -0.0000

Data Index: 281653 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.2252. Min Act: -0.0000

Data Index: 1251944 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.1643. Min Act: -0.0000

Data Index: 384166 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.1197. Min Act: -0.0000

Data Index: 1237382 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.1446. Min Act: -0.0000

Data Index: 1318899 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.1085. Min Act: -0.0001

Data Index: 1604119 (Python Code)

Max Activating Token Index: 875

Text #8

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.1341. Min Act: -0.0001

Data Index: 173888 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.0376. Min Act: -0.0000

Data Index: 246760 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.0571. Min Act: -0.0000

Data Index: 1301033 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.0686. Min Act: -0.0000

Data Index: 1122950 (C4 (Web Text))

Max Activating Token Index: 69

Text #12

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.0695. Min Act: -0.0001

Data Index: 555042 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.0271. Min Act: -0.0000

Data Index: 334830 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 1.7171. Min Range: -1.7171

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1047398 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 1.7171. Min Range: -1.7171

Max Act: 0.9538. Min Act: -0.0000

Data Index: 570734 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 1.7171. Min Range: -1.7171

Max Act: 1.0242. Min Act: -0.0000

Data Index: 1233327 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 1.7171. Min Range: -1.7171

Max Act: 0.9590. Min Act: -0.0000

Data Index: 20020 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 1.7171. Min Range: -1.7171

Max Act: 0.9325. Min Act: -0.0000

Data Index: 842876 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 1.7171. Min Range: -1.7171

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1067251 (C4 (Web Text))

Max Activating Token Index: 773