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

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

Neuron 3425 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1282. Min Range: -1.1282

Max Act: 1.1282. Min Act: -0.0000

Data Index: 340138 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.9899. Min Act: -0.0000

Data Index: 308131 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 1.1282. Min Range: -1.1282

Max Act: 1.0450. Min Act: -0.0000

Data Index: 519733 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.9304. Min Act: -0.0000

Data Index: 119378 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.9871. Min Act: -0.0000

Data Index: 1193209 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.8722. Min Act: -0.0000

Data Index: 19252 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.9006. Min Act: -0.0000

Data Index: 1230946 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.8096. Min Act: -0.0000

Data Index: 941425 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.8730. Min Act: -0.0000

Data Index: 53013 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7939. Min Act: -0.0000

Data Index: 973138 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.8130. Min Act: -0.0000

Data Index: 370595 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.8137. Min Act: -0.0000

Data Index: 1165625 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1048082 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7926. Min Act: -0.0000

Data Index: 558202 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.8107. Min Act: -0.0000

Data Index: 863951 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7911. Min Act: -0.0000

Data Index: 398583 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7647. Min Act: -0.0000

Data Index: 329282 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7391. Min Act: -0.0000

Data Index: 887491 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7976. Min Act: -0.0000

Data Index: 1017353 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1150636 (C4 (Web Text))

Max Activating Token Index: 564