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

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

Neuron 4577 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5644. Min Range: -3.5644

Max Act: 3.4644. Min Act: -0.0000

Data Index: 1030915 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 3.5644. Min Range: -3.5644

Max Act: 3.5644. Min Act: -0.0000

Data Index: 1112869 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 3.5644. Min Range: -3.5644

Max Act: 3.4955. Min Act: -0.0000

Data Index: 1348361 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 3.5644. Min Range: -3.5644

Max Act: 3.2124. Min Act: -0.0000

Data Index: 840600 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 3.5644. Min Range: -3.5644

Max Act: 3.2876. Min Act: -0.0000

Data Index: 68728 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 3.5644. Min Range: -3.5644

Max Act: 2.6695. Min Act: -0.0000

Data Index: 413117 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 3.5644. Min Range: -3.5644

Max Act: 2.3990. Min Act: -0.0000

Data Index: 755260 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 3.5644. Min Range: -3.5644

Max Act: 2.2969. Min Act: -0.0000

Data Index: 340594 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 3.5644. Min Range: -3.5644

Max Act: 2.5334. Min Act: -0.0000

Data Index: 205975 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 3.5644. Min Range: -3.5644

Max Act: 2.3761. Min Act: -0.0000

Data Index: 50049 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 3.5644. Min Range: -3.5644

Max Act: 2.2402. Min Act: -0.0000

Data Index: 399964 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 3.5644. Min Range: -3.5644

Max Act: 2.3348. Min Act: -0.0000

Data Index: 1027098 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 3.5644. Min Range: -3.5644

Max Act: 2.3301. Min Act: -0.0000

Data Index: 716099 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 3.5644. Min Range: -3.5644

Max Act: 2.3203. Min Act: -0.0000

Data Index: 1174094 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 3.5644. Min Range: -3.5644

Max Act: 2.2714. Min Act: -0.0000

Data Index: 758706 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 3.5644. Min Range: -3.5644

Max Act: 2.2267. Min Act: -0.0000

Data Index: 394970 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 3.5644. Min Range: -3.5644

Max Act: 2.1859. Min Act: -0.0000

Data Index: 487723 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 3.5644. Min Range: -3.5644

Max Act: 2.3074. Min Act: -0.0000

Data Index: 94679 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 3.5644. Min Range: -3.5644

Max Act: 2.2826. Min Act: -0.0000

Data Index: 392901 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 3.5644. Min Range: -3.5644

Max Act: 2.1718. Min Act: -0.0000

Data Index: 1147643 (C4 (Web Text))

Max Activating Token Index: 947