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

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

Neuron 4169 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1445438 (Python Code)

Max Activating Token Index: 188

Text #1

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1114. Min Act: -0.0002

Data Index: 1525330 (Python Code)

Max Activating Token Index: 347

Text #2

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1036. Min Act: -0.0002

Data Index: 1561962 (Python Code)

Max Activating Token Index: 187

Text #3

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1569756 (Python Code)

Max Activating Token Index: 88

Text #4

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1424991 (Python Code)

Max Activating Token Index: 290

Text #5

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0892. Min Act: -0.0002

Data Index: 1500232 (Python Code)

Max Activating Token Index: 857

Text #6

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1611369 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1527632 (Python Code)

Max Activating Token Index: 780

Text #8

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1534052 (Python Code)

Max Activating Token Index: 411

Text #9

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1525951 (Python Code)

Max Activating Token Index: 633

Text #10

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1590549 (Python Code)

Max Activating Token Index: 346

Text #11

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1522370 (Python Code)

Max Activating Token Index: 391

Text #12

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1513457 (Python Code)

Max Activating Token Index: 303

Text #13

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1389421 (Python Code)

Max Activating Token Index: 722

Text #14

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1639105 (Python Code)

Max Activating Token Index: 438

Text #15

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1496016 (Python Code)

Max Activating Token Index: 201

Text #16

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1432032 (Python Code)

Max Activating Token Index: 164

Text #17

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1432540 (Python Code)

Max Activating Token Index: 834

Text #18

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1395509 (Python Code)

Max Activating Token Index: 1003

Text #19

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1516201 (Python Code)

Max Activating Token Index: 372