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

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

Neuron 1265 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: 0.0809. Min Range: -0.0809

Max Act: 0.0797. Min Act: -0.0002

Data Index: 541376 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0808. Min Act: -0.0002

Data Index: 617924 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0809. Min Act: -0.0002

Data Index: 303835 (C4 (Web Text))

Max Activating Token Index: 160

Text #3

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1195520 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0755. Min Act: -0.0002

Data Index: 204641 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0755. Min Act: -0.0001

Data Index: 971896 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1232608 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0749. Min Act: -0.0002

Data Index: 296324 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0764. Min Act: 0.0001

Data Index: 1207793 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0734. Min Act: -0.0001

Data Index: 822054 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0748. Min Act: -0.0002

Data Index: 633355 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0759. Min Act: -0.0002

Data Index: 235821 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0715. Min Act: -0.0002

Data Index: 787188 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0737. Min Act: -0.0002

Data Index: 117600 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1326603 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0734. Min Act: -0.0002

Data Index: 22997 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0731. Min Act: 0.0002

Data Index: 267732 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0726. Min Act: -0.0001

Data Index: 468411 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1182938 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1125123 (C4 (Web Text))

Max Activating Token Index: 467