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

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

Neuron 3455 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: 1.6492. Min Range: -1.6492

Max Act: 1.6492. Min Act: -0.0000

Data Index: 737348 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.5915. Min Act: -0.0000

Data Index: 316586 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.5297. Min Act: -0.0000

Data Index: 616094 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.4760. Min Act: -0.0000

Data Index: 701680 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.3184. Min Act: -0.0000

Data Index: 1079089 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.2551. Min Act: -0.0000

Data Index: 13602 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.2449. Min Act: -0.0000

Data Index: 1273969 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.2196. Min Act: -0.0000

Data Index: 844946 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.1916. Min Act: -0.0000

Data Index: 281936 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.2178. Min Act: -0.0000

Data Index: 310073 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.2630. Min Act: -0.0000

Data Index: 580320 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.1734. Min Act: -0.0001

Data Index: 1089208 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.3167. Min Act: -0.0000

Data Index: 553273 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.2001. Min Act: -0.0000

Data Index: 564195 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.1921. Min Act: -0.0000

Data Index: 28037 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.1789. Min Act: -0.0000

Data Index: 462098 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1063074 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.0994. Min Act: -0.0000

Data Index: 897910 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.0991. Min Act: -0.0000

Data Index: 566548 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 1.6492. Min Range: -1.6492

Max Act: 1.1283. Min Act: -0.0001

Data Index: 356921 (C4 (Web Text))

Max Activating Token Index: 20