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

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

Neuron 464 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.8210. Min Act: -0.0000

Data Index: 1299200 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1217045 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5922. Min Act: -0.0000

Data Index: 508709 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6270. Min Act: -0.0000

Data Index: 69106 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6077. Min Act: -0.0000

Data Index: 196356 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5838. Min Act: -0.0000

Data Index: 345882 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5218. Min Act: -0.0000

Data Index: 652707 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5400. Min Act: -0.0000

Data Index: 134103 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5424. Min Act: -0.0000

Data Index: 1483861 (Python Code)

Max Activating Token Index: 861

Text #9

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5528. Min Act: -0.0000

Data Index: 758223 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5483. Min Act: -0.0000

Data Index: 457811 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5709. Min Act: -0.0000

Data Index: 851441 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5390. Min Act: -0.0000

Data Index: 730802 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6000. Min Act: -0.0000

Data Index: 751493 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1235907 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1629146 (Python Code)

Max Activating Token Index: 207

Text #16

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5280. Min Act: -0.0000

Data Index: 863876 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5290. Min Act: -0.0000

Data Index: 110089 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5108. Min Act: -0.0000

Data Index: 535132 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1042027 (C4 (Web Text))

Max Activating Token Index: 965