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

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

Neuron 397 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: 0.1064. Min Range: -0.1064

Max Act: 0.1064. Min Act: -0.0005

Data Index: 384616 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.1012. Min Act: -0.0005

Data Index: 467025 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0918. Min Act: -0.0005

Data Index: 1065103 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0843. Min Act: -0.0005

Data Index: 1019984 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0840. Min Act: -0.0005

Data Index: 273354 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0918. Min Act: -0.0005

Data Index: 158980 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0806. Min Act: -0.0005

Data Index: 75512 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0762. Min Act: -0.0005

Data Index: 639126 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0799. Min Act: -0.0005

Data Index: 514012 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0784. Min Act: -0.0005

Data Index: 372684 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0805. Min Act: -0.0005

Data Index: 733341 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0772. Min Act: -0.0005

Data Index: 1265579 (C4 (Web Text))

Max Activating Token Index: 418

Text #12

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0798. Min Act: -0.0005

Data Index: 1014076 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0745. Min Act: -0.0005

Data Index: 755457 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0775. Min Act: -0.0005

Data Index: 1028650 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0765. Min Act: -0.0005

Data Index: 1218534 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0805. Min Act: -0.0005

Data Index: 111999 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0730. Min Act: -0.0005

Data Index: 869335 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0766. Min Act: -0.0005

Data Index: 402928 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.1064. Min Range: -0.1064

Max Act: 0.0743. Min Act: -0.0005

Data Index: 497667 (C4 (Web Text))

Max Activating Token Index: 44