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

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

Neuron 1140 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: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0002

Data Index: 200983 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0731. Min Act: -0.0002

Data Index: 460640 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0716. Min Act: -0.0002

Data Index: 176219 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0725. Min Act: -0.0002

Data Index: 718775 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0683. Min Act: -0.0002

Data Index: 413552 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0695. Min Act: -0.0002

Data Index: 916116 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0677. Min Act: -0.0002

Data Index: 80579 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0678. Min Act: -0.0002

Data Index: 160062 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1216993 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0676. Min Act: -0.0002

Data Index: 97909 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0675. Min Act: -0.0002

Data Index: 763738 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1046866 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1255859 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0669. Min Act: -0.0002

Data Index: 334610 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1228965 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0647. Min Act: -0.0002

Data Index: 950937 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1059304 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0651. Min Act: -0.0002

Data Index: 811840 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0653. Min Act: -0.0002

Data Index: 543034 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0653. Min Act: -0.0002

Data Index: 968378 (C4 (Web Text))

Max Activating Token Index: 906