Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1070 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0887. Min Act: -0.0005

Data Index: 1066221 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0869. Min Act: -0.0005

Data Index: 39521 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0836. Min Act: -0.0005

Data Index: 949094 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0858. Min Act: -0.0005

Data Index: 111730 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0801. Min Act: -0.0005

Data Index: 289359 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0822. Min Act: -0.0005

Data Index: 843073 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0777. Min Act: -0.0005

Data Index: 922169 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0766. Min Act: -0.0005

Data Index: 1100458 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0713. Min Act: -0.0005

Data Index: 995716 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0701. Min Act: -0.0005

Data Index: 619919 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0709. Min Act: -0.0005

Data Index: 528833 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0712. Min Act: -0.0005

Data Index: 66431 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0734. Min Act: -0.0005

Data Index: 648242 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0754. Min Act: -0.0005

Data Index: 918406 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0724. Min Act: -0.0005

Data Index: 621095 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0703. Min Act: -0.0005

Data Index: 563156 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0623. Min Act: -0.0005

Data Index: 199288 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0671. Min Act: -0.0005

Data Index: 390548 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0720. Min Act: -0.0005

Data Index: 775773 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.0887. Min Range: -0.0887

Max Act: 0.0687. Min Act: -0.0004

Data Index: 232424 (C4 (Web Text))

Max Activating Token Index: 557