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

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

Neuron 3255 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8560. Min Range: -2.8560

Max Act: 2.8560. Min Act: -0.0000

Data Index: 1126773 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 2.8560. Min Range: -2.8560

Max Act: 2.5067. Min Act: -0.0000

Data Index: 219838 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 2.8560. Min Range: -2.8560

Max Act: 2.5300. Min Act: -0.0000

Data Index: 722088 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 2.8560. Min Range: -2.8560

Max Act: 2.3276. Min Act: -0.0000

Data Index: 31636 (C4 (Web Text))

Max Activating Token Index: 396

Text #4

Max Range: 2.8560. Min Range: -2.8560

Max Act: 2.2219. Min Act: -0.0000

Data Index: 1141217 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 2.8560. Min Range: -2.8560

Max Act: 2.2028. Min Act: -0.0000

Data Index: 663362 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 2.8560. Min Range: -2.8560

Max Act: 2.0751. Min Act: -0.0000

Data Index: 1180301 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 2.8560. Min Range: -2.8560

Max Act: 2.0339. Min Act: -0.0000

Data Index: 1115514 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 2.8560. Min Range: -2.8560

Max Act: 2.1115. Min Act: -0.0000

Data Index: 725968 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 2.8560. Min Range: -2.8560

Max Act: 1.9079. Min Act: -0.0000

Data Index: 1118787 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 2.8560. Min Range: -2.8560

Max Act: 1.9877. Min Act: -0.0000

Data Index: 1234414 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 2.8560. Min Range: -2.8560

Max Act: 1.9802. Min Act: -0.0000

Data Index: 790750 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 2.8560. Min Range: -2.8560

Max Act: 1.8894. Min Act: -0.0000

Data Index: 219021 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 2.8560. Min Range: -2.8560

Max Act: 2.2018. Min Act: -0.0000

Data Index: 151290 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 2.8560. Min Range: -2.8560

Max Act: 1.8619. Min Act: -0.0000

Data Index: 699939 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 2.8560. Min Range: -2.8560

Max Act: 1.8918. Min Act: -0.0000

Data Index: 1234651 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 2.8560. Min Range: -2.8560

Max Act: 1.9209. Min Act: -0.0000

Data Index: 91722 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 2.8560. Min Range: -2.8560

Max Act: 1.9124. Min Act: -0.0000

Data Index: 427515 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 2.8560. Min Range: -2.8560

Max Act: 1.9968. Min Act: -0.0000

Data Index: 375700 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 2.8560. Min Range: -2.8560

Max Act: 1.8772. Min Act: -0.0000

Data Index: 152339 (C4 (Web Text))

Max Activating Token Index: 542