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

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

Neuron 354 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1183. Min Act: -0.0002

Data Index: 508495 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.1010. Min Act: -0.0002

Data Index: 77045 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0923. Min Act: -0.0002

Data Index: 891020 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0804. Min Act: -0.0002

Data Index: 880832 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0835. Min Act: -0.0002

Data Index: 871644 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0874. Min Act: -0.0002

Data Index: 249021 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0787. Min Act: -0.0002

Data Index: 706409 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0783. Min Act: -0.0002

Data Index: 921400 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0760. Min Act: -0.0002

Data Index: 300625 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0750. Min Act: -0.0002

Data Index: 916359 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0746. Min Act: -0.0002

Data Index: 4626 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1247359 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0736. Min Act: -0.0002

Data Index: 476462 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0723. Min Act: -0.0002

Data Index: 1310743 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0755. Min Act: -0.0002

Data Index: 963928 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0793. Min Act: -0.0002

Data Index: 339426 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0692. Min Act: -0.0002

Data Index: 618670 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0710. Min Act: -0.0002

Data Index: 656952 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0733. Min Act: -0.0002

Data Index: 125114 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.1183. Min Range: -0.1183

Max Act: 0.0698. Min Act: -0.0002

Data Index: 942410 (C4 (Web Text))

Max Activating Token Index: 623