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

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

Neuron 1090 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: 0.1122. Min Range: -0.1122

Max Act: 0.1122. Min Act: -0.0002

Data Index: 1247464 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0970. Min Act: -0.0002

Data Index: 1304520 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0933. Min Act: -0.0002

Data Index: 974292 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0862. Min Act: -0.0002

Data Index: 513340 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0818. Min Act: -0.0002

Data Index: 907743 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1068541 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0812. Min Act: -0.0002

Data Index: 621000 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1029172 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0806. Min Act: -0.0002

Data Index: 386568 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0781. Min Act: -0.0002

Data Index: 170171 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0809. Min Act: -0.0002

Data Index: 53363 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0800. Min Act: -0.0002

Data Index: 1034333 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0769. Min Act: -0.0002

Data Index: 454550 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0800. Min Act: -0.0002

Data Index: 275880 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0750. Min Act: -0.0002

Data Index: 474287 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0816. Min Act: -0.0002

Data Index: 852423 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0774. Min Act: -0.0002

Data Index: 629133 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1303150 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0780. Min Act: -0.0002

Data Index: 540078 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.1122. Min Range: -0.1122

Max Act: 0.0771. Min Act: -0.0002

Data Index: 527788 (C4 (Web Text))

Max Activating Token Index: 507