Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1452 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6875. Min Act: -0.0000

Data Index: 144689 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1197348 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1175050 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.6077. Min Act: -0.0000

Data Index: 261166 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5715. Min Act: -0.0000

Data Index: 333540 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5259. Min Act: -0.0000

Data Index: 538850 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5423. Min Act: -0.0000

Data Index: 196616 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5639. Min Act: -0.0000

Data Index: 427229 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5859. Min Act: -0.0000

Data Index: 55673 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5596. Min Act: -0.0000

Data Index: 115725 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5183. Min Act: -0.0000

Data Index: 246049 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1098203 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1092953 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5195. Min Act: -0.0000

Data Index: 942648 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4964. Min Act: -0.0000

Data Index: 591359 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5139. Min Act: -0.0000

Data Index: 1126473 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5057. Min Act: -0.0000

Data Index: 322687 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.5501. Min Act: -0.0000

Data Index: 739954 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1156444 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 0.6875. Min Range: -0.6875

Max Act: 0.4891. Min Act: -0.0000

Data Index: 662057 (C4 (Web Text))

Max Activating Token Index: 303