Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2962 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.8045. Min Act: -0.0001

Data Index: 1037574 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7816. Min Act: -0.0001

Data Index: 131443 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7079. Min Act: -0.0001

Data Index: 681405 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.6542. Min Act: -0.0001

Data Index: 888896 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7096. Min Act: -0.0001

Data Index: 756932 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.6856. Min Act: -0.0001

Data Index: 1350095 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.6671. Min Act: -0.0001

Data Index: 765545 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.6857. Min Act: -0.0000

Data Index: 339243 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.6331. Min Act: -0.0001

Data Index: 831148 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.6141. Min Act: -0.0001

Data Index: 127894 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5611. Min Act: -0.0001

Data Index: 413645 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.6372. Min Act: -0.0001

Data Index: 608678 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.6295. Min Act: -0.0001

Data Index: 1039187 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5876. Min Act: -0.0001

Data Index: 733405 (C4 (Web Text))

Max Activating Token Index: 366

Text #14

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5710. Min Act: -0.0001

Data Index: 546356 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.6579. Min Act: -0.0001

Data Index: 713817 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1160263 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5841. Min Act: -0.0000

Data Index: 216529 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5619. Min Act: -0.0001

Data Index: 750543 (C4 (Web Text))

Max Activating Token Index: 607

Text #19

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.6674. Min Act: -0.0000

Data Index: 211995 (C4 (Web Text))

Max Activating Token Index: 335