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

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

Neuron 3640 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: 2.3102. Min Range: -2.3102

Max Act: 2.3102. Min Act: -0.0000

Data Index: 547691 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 2.3102. Min Range: -2.3102

Max Act: 2.0783. Min Act: -0.0000

Data Index: 943816 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.8137. Min Act: -0.0000

Data Index: 741444 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.7599. Min Act: -0.0000

Data Index: 452512 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.6856. Min Act: -0.0000

Data Index: 550421 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.6202. Min Act: -0.0000

Data Index: 146699 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.6237. Min Act: -0.0000

Data Index: 1074158 (C4 (Web Text))

Max Activating Token Index: 444

Text #7

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.7220. Min Act: -0.0000

Data Index: 607224 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.5715. Min Act: -0.0000

Data Index: 675057 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.5143. Min Act: -0.0000

Data Index: 45664 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.5071. Min Act: -0.0000

Data Index: 54395 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.4843. Min Act: -0.0000

Data Index: 888579 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.5360. Min Act: -0.0000

Data Index: 104635 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.4339. Min Act: -0.0000

Data Index: 199014 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.3304. Min Act: -0.0000

Data Index: 1225942 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.4044. Min Act: -0.0000

Data Index: 271969 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.3573. Min Act: -0.0000

Data Index: 897744 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.3498. Min Act: -0.0000

Data Index: 912794 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.2974. Min Act: -0.0000

Data Index: 1288225 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 2.3102. Min Range: -2.3102

Max Act: 1.3080. Min Act: -0.0000

Data Index: 1181562 (C4 (Web Text))

Max Activating Token Index: 637