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

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

Neuron 4515 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.8285. Min Act: -0.0000

Data Index: 689926 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1149090 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6826. Min Act: -0.0000

Data Index: 284359 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6824. Min Act: -0.0000

Data Index: 662118 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.7029. Min Act: 0.0000

Data Index: 924507 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6788. Min Act: 0.0000

Data Index: 640394 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1208490 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6632. Min Act: -0.0000

Data Index: 42125 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6547. Min Act: -0.0000

Data Index: 1130111 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1035277 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.7064. Min Act: -0.0000

Data Index: 410458 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6046. Min Act: -0.0000

Data Index: 411504 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6057. Min Act: -0.0000

Data Index: 688267 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.5871. Min Act: -0.0000

Data Index: 656124 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.6064. Min Act: -0.0000

Data Index: 582276 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1197582 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.5901. Min Act: -0.0000

Data Index: 342868 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.5909. Min Act: -0.0000

Data Index: 890509 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.5522. Min Act: -0.0000

Data Index: 141576 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.8285. Min Range: -0.8285

Max Act: 0.5902. Min Act: -0.0000

Data Index: 312666 (C4 (Web Text))

Max Activating Token Index: 440