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

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

Neuron 5609 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0753. Min Act: -0.0001

Data Index: 740229 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0847. Min Act: -0.0001

Data Index: 1209210 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0767. Min Act: -0.0001

Data Index: 1302837 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0723. Min Act: -0.0001

Data Index: 483553 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0721. Min Act: -0.0001

Data Index: 666975 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0717. Min Act: -0.0001

Data Index: 838280 (C4 (Web Text))

Max Activating Token Index: 81

Text #6

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0717. Min Act: -0.0001

Data Index: 490634 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0733. Min Act: -0.0001

Data Index: 261649 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0706. Min Act: -0.0001

Data Index: 263598 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0661. Min Act: -0.0001

Data Index: 177822 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1238320 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0675. Min Act: -0.0001

Data Index: 848937 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0668. Min Act: -0.0001

Data Index: 840579 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0668. Min Act: -0.0001

Data Index: 987855 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0688. Min Act: -0.0001

Data Index: 734566 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1219928 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0663. Min Act: -0.0001

Data Index: 49716 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0662. Min Act: -0.0001

Data Index: 181211 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0729. Min Act: -0.0001

Data Index: 863651 (C4 (Web Text))

Max Activating Token Index: 327

Text #19

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0676. Min Act: -0.0001

Data Index: 41814 (C4 (Web Text))

Max Activating Token Index: 886