Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1606 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0815. Min Act: -0.0003

Data Index: 1155203 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0894. Min Act: -0.0003

Data Index: 958872 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0891. Min Act: -0.0003

Data Index: 1076862 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0885. Min Act: -0.0003

Data Index: 1111362 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0884. Min Act: -0.0003

Data Index: 935951 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0881. Min Act: -0.0003

Data Index: 920366 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0852. Min Act: -0.0003

Data Index: 354681 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0872. Min Act: -0.0003

Data Index: 42077 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0859. Min Act: -0.0003

Data Index: 780161 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0860. Min Act: -0.0003

Data Index: 1280252 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0889. Min Act: -0.0003

Data Index: 769818 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0830. Min Act: -0.0003

Data Index: 1032686 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0817. Min Act: -0.0003

Data Index: 176813 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0845. Min Act: -0.0003

Data Index: 892513 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0849. Min Act: -0.0003

Data Index: 548479 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0841. Min Act: -0.0003

Data Index: 169609 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0833. Min Act: -0.0003

Data Index: 926988 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0801. Min Act: -0.0003

Data Index: 1341056 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0830. Min Act: -0.0003

Data Index: 180125 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.0894. Min Range: -0.0894

Max Act: 0.0800. Min Act: -0.0003

Data Index: 1121389 (C4 (Web Text))

Max Activating Token Index: 352