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

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

Neuron 5064 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.4102. Min Act: -0.0001

Data Index: 609719 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.4067. Min Act: -0.0001

Data Index: 913821 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.2312. Min Act: -0.0001

Data Index: 307420 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.1941. Min Act: -0.0001

Data Index: 278148 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.1910. Min Act: -0.0001

Data Index: 916693 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.1715. Min Act: -0.0001

Data Index: 677875 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.3797. Min Act: -0.0001

Data Index: 1177809 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.2247. Min Act: -0.0001

Data Index: 451877 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.0393. Min Act: -0.0001

Data Index: 123612 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.0645. Min Act: -0.0001

Data Index: 990867 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.9908. Min Act: -0.0001

Data Index: 364726 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.0779. Min Act: -0.0001

Data Index: 64370 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.1073. Min Act: -0.0001

Data Index: 865901 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.1047. Min Act: -0.0001

Data Index: 1044284 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.1235. Min Act: -0.0001

Data Index: 1165655 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 1.4102. Min Range: -1.4102

Max Act: 0.9596. Min Act: -0.0001

Data Index: 1015752 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.0918. Min Act: -0.0001

Data Index: 1295425 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.0763. Min Act: -0.0001

Data Index: 964166 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.0772. Min Act: -0.0001

Data Index: 1290574 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 1.4102. Min Range: -1.4102

Max Act: 1.0531. Min Act: -0.0001

Data Index: 709154 (C4 (Web Text))

Max Activating Token Index: 275