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

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

Neuron 1374 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: 0.1079. Min Range: -0.1079

Max Act: 0.1079. Min Act: -0.0002

Data Index: 424979 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0999. Min Act: -0.0001

Data Index: 366651 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0939. Min Act: -0.0002

Data Index: 101291 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0928. Min Act: -0.0002

Data Index: 163026 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0936. Min Act: -0.0002

Data Index: 310568 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1292165 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0890. Min Act: -0.0002

Data Index: 529681 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0868. Min Act: -0.0002

Data Index: 768339 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0858. Min Act: -0.0001

Data Index: 1181628 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0860. Min Act: -0.0002

Data Index: 642747 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0853. Min Act: -0.0002

Data Index: 229283 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0829. Min Act: -0.0002

Data Index: 436919 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0829. Min Act: -0.0002

Data Index: 86919 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0824. Min Act: -0.0002

Data Index: 250206 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0827. Min Act: -0.0002

Data Index: 109559 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0823. Min Act: -0.0002

Data Index: 620753 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0827. Min Act: -0.0002

Data Index: 495016 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0807. Min Act: -0.0002

Data Index: 254132 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0822. Min Act: -0.0002

Data Index: 1324112 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.1079. Min Range: -0.1079

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1005945 (C4 (Web Text))

Max Activating Token Index: 71