Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4637 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1687. Min Range: -1.1687

Max Act: 1.1687. Min Act: -0.0000

Data Index: 1311770 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1211620 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1334528 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.9163. Min Act: -0.0000

Data Index: 898545 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 1.1687. Min Range: -1.1687

Max Act: 1.0100. Min Act: -0.0000

Data Index: 94212 (C4 (Web Text))

Max Activating Token Index: 827

Text #5

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.8164. Min Act: -0.0000

Data Index: 640243 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.8397. Min Act: -0.0000

Data Index: 417290 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.7817. Min Act: -0.0000

Data Index: 280122 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1176821 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.8021. Min Act: -0.0000

Data Index: 532730 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.6731. Min Act: -0.0000

Data Index: 974847 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.6914. Min Act: -0.0000

Data Index: 622717 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.7229. Min Act: -0.0000

Data Index: 196377 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1038183 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.7377. Min Act: -0.0000

Data Index: 733720 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.6871. Min Act: -0.0000

Data Index: 519978 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1121816 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.6801. Min Act: -0.0000

Data Index: 312179 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.7067. Min Act: -0.0000

Data Index: 872190 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 1.1687. Min Range: -1.1687

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1318451 (C4 (Web Text))

Max Activating Token Index: 974