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

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

Neuron 1083 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0874. Min Act: -0.0002

Data Index: 623542 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1137102 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1209176 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0817. Min Act: -0.0001

Data Index: 1217432 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0835. Min Act: -0.0002

Data Index: 707275 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0804. Min Act: -0.0002

Data Index: 802774 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0825. Min Act: -0.0001

Data Index: 669077 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0813. Min Act: -0.0002

Data Index: 462844 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0800. Min Act: -0.0001

Data Index: 470822 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0816. Min Act: -0.0001

Data Index: 1337735 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0776. Min Act: -0.0002

Data Index: 948887 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0766. Min Act: -0.0002

Data Index: 468624 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1303326 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0745. Min Act: -0.0002

Data Index: 952502 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0746. Min Act: -0.0002

Data Index: 823379 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0745. Min Act: -0.0002

Data Index: 720324 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1147540 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0731. Min Act: 0.0000

Data Index: 823679 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0724. Min Act: -0.0002

Data Index: 326291 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0748. Min Act: -0.0001

Data Index: 211612 (C4 (Web Text))

Max Activating Token Index: 697