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

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

Neuron 4422 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.3072. Min Act: -0.0000

Data Index: 636519 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.3171. Min Act: -0.0000

Data Index: 1307894 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1175608 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1760. Min Act: -0.0000

Data Index: 443310 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1842. Min Act: -0.0000

Data Index: 362756 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1767. Min Act: -0.0000

Data Index: 22821 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.0869. Min Act: -0.0000

Data Index: 273825 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.0311. Min Act: -0.0000

Data Index: 108658 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1203. Min Act: -0.0000

Data Index: 1174476 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.0476. Min Act: -0.0000

Data Index: 456535 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.0998. Min Act: -0.0000

Data Index: 707880 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.0885. Min Act: -0.0000

Data Index: 404223 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.0812. Min Act: -0.0000

Data Index: 85044 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1289. Min Act: -0.0000

Data Index: 1078997 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1207. Min Act: -0.0000

Data Index: 1343064 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 1.3171. Min Range: -1.3171

Max Act: 0.9884. Min Act: -0.0000

Data Index: 819004 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.1113. Min Act: -0.0000

Data Index: 588520 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 1.3171. Min Range: -1.3171

Max Act: 1.0795. Min Act: -0.0000

Data Index: 430893 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 1.3171. Min Range: -1.3171

Max Act: 0.9702. Min Act: -0.0000

Data Index: 221190 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 1.3171. Min Range: -1.3171

Max Act: 0.9917. Min Act: -0.0000

Data Index: 12899 (C4 (Web Text))

Max Activating Token Index: 56