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

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

Neuron 2099 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: 2.7433. Min Range: -2.7433

Max Act: 2.7433. Min Act: -0.0000

Data Index: 149182 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.9009. Min Act: -0.0000

Data Index: 157841 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.7588. Min Act: -0.0000

Data Index: 275060 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.6311. Min Act: -0.0000

Data Index: 987138 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.5922. Min Act: -0.0000

Data Index: 421789 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.5648. Min Act: -0.0000

Data Index: 99810 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.5192. Min Act: -0.0000

Data Index: 170145 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.5234. Min Act: -0.0000

Data Index: 178942 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.4030. Min Act: -0.0000

Data Index: 459316 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.3923. Min Act: -0.0000

Data Index: 1157669 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.4605. Min Act: -0.0000

Data Index: 881899 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.5449. Min Act: -0.0000

Data Index: 1093867 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.4470. Min Act: -0.0000

Data Index: 447696 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.4083. Min Act: -0.0000

Data Index: 638532 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.3763. Min Act: -0.0000

Data Index: 602922 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.3753. Min Act: -0.0000

Data Index: 540178 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.2778. Min Act: -0.0000

Data Index: 147671 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.4416. Min Act: -0.0000

Data Index: 1271096 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.3892. Min Act: -0.0000

Data Index: 227680 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 2.7433. Min Range: -2.7433

Max Act: 1.4678. Min Act: -0.0000

Data Index: 127892 (C4 (Web Text))

Max Activating Token Index: 783