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

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

Neuron 252 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3967. Min Range: -5.3967

Max Act: 5.1270. Min Act: -0.0001

Data Index: 200238 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 5.3967. Min Range: -5.3967

Max Act: 5.3967. Min Act: -0.0001

Data Index: 48995 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 5.3967. Min Range: -5.3967

Max Act: 5.1383. Min Act: -0.0001

Data Index: 124868 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 5.3967. Min Range: -5.3967

Max Act: 5.2839. Min Act: -0.0001

Data Index: 22482 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 5.3967. Min Range: -5.3967

Max Act: 4.9126. Min Act: -0.0001

Data Index: 1002205 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 5.3967. Min Range: -5.3967

Max Act: 4.8727. Min Act: -0.0001

Data Index: 701921 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 5.3967. Min Range: -5.3967

Max Act: 5.0264. Min Act: -0.0001

Data Index: 1198253 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 5.3967. Min Range: -5.3967

Max Act: 4.8788. Min Act: -0.0001

Data Index: 645071 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 5.3967. Min Range: -5.3967

Max Act: 4.8126. Min Act: -0.0001

Data Index: 54157 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 5.3967. Min Range: -5.3967

Max Act: 4.6417. Min Act: -0.0001

Data Index: 832889 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 5.3967. Min Range: -5.3967

Max Act: 4.6584. Min Act: -0.0001

Data Index: 357818 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 5.3967. Min Range: -5.3967

Max Act: 4.7639. Min Act: -0.0001

Data Index: 739910 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 5.3967. Min Range: -5.3967

Max Act: 5.0918. Min Act: -0.0001

Data Index: 464754 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 5.3967. Min Range: -5.3967

Max Act: 4.6962. Min Act: -0.0001

Data Index: 14607 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 5.3967. Min Range: -5.3967

Max Act: 4.6624. Min Act: -0.0001

Data Index: 98981 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 5.3967. Min Range: -5.3967

Max Act: 4.8632. Min Act: -0.0001

Data Index: 291647 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 5.3967. Min Range: -5.3967

Max Act: 4.8591. Min Act: -0.0001

Data Index: 639307 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 5.3967. Min Range: -5.3967

Max Act: 4.6132. Min Act: -0.0001

Data Index: 90822 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 5.3967. Min Range: -5.3967

Max Act: 4.5531. Min Act: -0.0001

Data Index: 747555 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 5.3967. Min Range: -5.3967

Max Act: 4.8797. Min Act: -0.0001

Data Index: 672719 (C4 (Web Text))

Max Activating Token Index: 222