Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3984 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.1035. Min Act: -0.0000

Data Index: 140102 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0994. Min Act: -0.0000

Data Index: 925010 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0870. Min Act: -0.0000

Data Index: 460420 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0902. Min Act: -0.0000

Data Index: 639293 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0860. Min Act: -0.0000

Data Index: 852850 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0830. Min Act: -0.0001

Data Index: 1384115 (Python Code)

Max Activating Token Index: 235

Text #6

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0898. Min Act: -0.0001

Data Index: 1648229 (Python Code)

Max Activating Token Index: 948

Text #7

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0810. Min Act: -0.0001

Data Index: 1481140 (Python Code)

Max Activating Token Index: 74

Text #8

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1279332 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0732. Min Act: -0.0000

Data Index: 761159 (C4 (Web Text))

Max Activating Token Index: 871

Text #10

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0756. Min Act: -0.0000

Data Index: 98336 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0753. Min Act: -0.0001

Data Index: 1396175 (Python Code)

Max Activating Token Index: 980

Text #12

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1019009 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0742. Min Act: -0.0001

Data Index: 303178 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0762. Min Act: -0.0001

Data Index: 809661 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0708. Min Act: -0.0001

Data Index: 883162 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0724. Min Act: -0.0000

Data Index: 1216975 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0767. Min Act: -0.0000

Data Index: 374218 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0742. Min Act: -0.0000

Data Index: 248487 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.1035. Min Range: -0.1035

Max Act: 0.0681. Min Act: -0.0001

Data Index: 701219 (C4 (Web Text))

Max Activating Token Index: 383