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

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

Neuron 972 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: 0.9156. Min Range: -0.9156

Max Act: 0.9156. Min Act: -0.0002

Data Index: 744862 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.7827. Min Act: -0.0003

Data Index: 671112 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.7509. Min Act: -0.0002

Data Index: 1051866 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.7912. Min Act: -0.0003

Data Index: 1125228 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6737. Min Act: -0.0003

Data Index: 564617 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6110. Min Act: -0.0003

Data Index: 395723 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.8295. Min Act: -0.0003

Data Index: 338178 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6199. Min Act: -0.0003

Data Index: 1581269 (Python Code)

Max Activating Token Index: 988

Text #8

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6767. Min Act: -0.0003

Data Index: 1228843 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.7406. Min Act: -0.0002

Data Index: 812094 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6275. Min Act: -0.0003

Data Index: 94295 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6607. Min Act: -0.0003

Data Index: 786921 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6550. Min Act: -0.0002

Data Index: 381505 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6068. Min Act: -0.0003

Data Index: 1266918 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6017. Min Act: -0.0003

Data Index: 1354399 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.5616. Min Act: -0.0003

Data Index: 946461 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6353. Min Act: -0.0003

Data Index: 305521 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6139. Min Act: -0.0002

Data Index: 22281 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.5952. Min Act: -0.0003

Data Index: 828963 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.9156. Min Range: -0.9156

Max Act: 0.6163. Min Act: -0.0003

Data Index: 838462 (C4 (Web Text))

Max Activating Token Index: 336