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

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

Neuron 3918 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2887. Min Range: -1.2887

Max Act: 1.2887. Min Act: -0.0000

Data Index: 121808 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.7609. Min Act: -0.0000

Data Index: 935423 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.8382. Min Act: -0.0000

Data Index: 178598 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1305811 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.8020. Min Act: -0.0001

Data Index: 1115633 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.8502. Min Act: -0.0000

Data Index: 797473 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.8750. Min Act: -0.0000

Data Index: 430896 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.8281. Min Act: -0.0000

Data Index: 605199 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.8574. Min Act: -0.0000

Data Index: 122033 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.8142. Min Act: -0.0001

Data Index: 972480 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.7242. Min Act: -0.0000

Data Index: 1093969 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.8004. Min Act: -0.0001

Data Index: 484913 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.7954. Min Act: -0.0000

Data Index: 139956 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.8046. Min Act: -0.0001

Data Index: 236105 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.7543. Min Act: -0.0000

Data Index: 894319 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.7998. Min Act: -0.0000

Data Index: 673137 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.7755. Min Act: -0.0000

Data Index: 117027 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.7552. Min Act: -0.0000

Data Index: 470204 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.8223. Min Act: -0.0000

Data Index: 860748 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.7714. Min Act: -0.0000

Data Index: 696406 (C4 (Web Text))

Max Activating Token Index: 989