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

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

Neuron 2150 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.9285. Min Act: -0.0000

Data Index: 561934 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.7056. Min Act: -0.0000

Data Index: 775652 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.6923. Min Act: -0.0000

Data Index: 706744 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.6606. Min Act: -0.0000

Data Index: 87565 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.6595. Min Act: -0.0000

Data Index: 172863 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.6154. Min Act: -0.0000

Data Index: 1233856 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.6472. Min Act: -0.0000

Data Index: 655632 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1183319 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.5755. Min Act: -0.0000

Data Index: 743660 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.5362. Min Act: -0.0000

Data Index: 457992 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1331173 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.5644. Min Act: -0.0000

Data Index: 839455 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.5306. Min Act: -0.0000

Data Index: 384677 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.5230. Min Act: -0.0000

Data Index: 531049 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1171202 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.5132. Min Act: -0.0000

Data Index: 836650 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.5318. Min Act: -0.0000

Data Index: 223724 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.5221. Min Act: -0.0000

Data Index: 181596 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1315313 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.9285. Min Range: -0.9285

Max Act: 0.4964. Min Act: -0.0000

Data Index: 191654 (C4 (Web Text))

Max Activating Token Index: 67