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

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

Neuron 845 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0790. Min Act: -0.0006

Data Index: 16452 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0715. Min Act: -0.0006

Data Index: 1161820 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0720. Min Act: -0.0006

Data Index: 1040871 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0756. Min Act: -0.0006

Data Index: 977663 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0710. Min Act: -0.0006

Data Index: 892394 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0752. Min Act: -0.0006

Data Index: 1274441 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0721. Min Act: -0.0006

Data Index: 645770 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0711. Min Act: -0.0006

Data Index: 1286640 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0697. Min Act: -0.0006

Data Index: 1241535 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0640. Min Act: -0.0006

Data Index: 579184 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0704. Min Act: -0.0006

Data Index: 946076 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0701. Min Act: -0.0006

Data Index: 667713 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0714. Min Act: -0.0006

Data Index: 769449 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0722. Min Act: -0.0006

Data Index: 738963 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0678. Min Act: -0.0006

Data Index: 63050 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0702. Min Act: -0.0006

Data Index: 708882 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0668. Min Act: -0.0006

Data Index: 1044127 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0654. Min Act: -0.0006

Data Index: 273241 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0679. Min Act: -0.0006

Data Index: 354803 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.0790. Min Range: -0.0790

Max Act: 0.0675. Min Act: -0.0006

Data Index: 675398 (C4 (Web Text))

Max Activating Token Index: 80