Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3575 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.6709. Min Act: -0.0001

Data Index: 1250247 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.6204. Min Act: -0.0001

Data Index: 993145 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.6415. Min Act: -0.0001

Data Index: 149818 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.6065. Min Act: -0.0001

Data Index: 605156 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.6022. Min Act: -0.0001

Data Index: 875862 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.6042. Min Act: -0.0001

Data Index: 544401 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.6109. Min Act: -0.0001

Data Index: 1409987 (Python Code)

Max Activating Token Index: 507

Text #7

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5757. Min Act: -0.0001

Data Index: 252299 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5666. Min Act: -0.0001

Data Index: 861560 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5668. Min Act: -0.0001

Data Index: 13814 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5815. Min Act: -0.0001

Data Index: 179147 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5619. Min Act: -0.0001

Data Index: 759873 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5595. Min Act: -0.0001

Data Index: 1207267 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5411. Min Act: -0.0001

Data Index: 754861 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5726. Min Act: -0.0001

Data Index: 957846 (C4 (Web Text))

Max Activating Token Index: 279

Text #15

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5726. Min Act: -0.0001

Data Index: 1248174 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5344. Min Act: -0.0001

Data Index: 1358372 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5667. Min Act: -0.0001

Data Index: 419802 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5425. Min Act: -0.0001

Data Index: 1025795 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.6709. Min Range: -0.6709

Max Act: 0.5072. Min Act: -0.0001

Data Index: 359921 (C4 (Web Text))

Max Activating Token Index: 91