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

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

Neuron 3379 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: 0.1214. Min Range: -0.1214

Max Act: 0.1214. Min Act: -0.0000

Data Index: 390838 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1115. Min Act: -0.0000

Data Index: 93308 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.1050. Min Act: -0.0000

Data Index: 55947 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0973. Min Act: -0.0000

Data Index: 331707 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0874. Min Act: -0.0000

Data Index: 370086 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0920. Min Act: -0.0000

Data Index: 122694 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1149151 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1228171 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1250144 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0978. Min Act: -0.0000

Data Index: 862256 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0936. Min Act: -0.0000

Data Index: 231491 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1319467 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0862. Min Act: -0.0000

Data Index: 664849 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0824. Min Act: -0.0000

Data Index: 184067 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0863. Min Act: -0.0000

Data Index: 908688 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0833. Min Act: -0.0000

Data Index: 483025 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0830. Min Act: -0.0000

Data Index: 1050334 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0828. Min Act: -0.0000

Data Index: 601330 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0830. Min Act: -0.0000

Data Index: 497472 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.1214. Min Range: -0.1214

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1100482 (C4 (Web Text))

Max Activating Token Index: 469