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

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

Neuron 4826 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.6412. Min Act: -0.0000

Data Index: 136822 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.6848. Min Act: -0.0000

Data Index: 733393 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.5680. Min Act: -0.0000

Data Index: 890776 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.6123. Min Act: -0.0000

Data Index: 197713 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.5827. Min Act: -0.0000

Data Index: 245286 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1312320 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.5687. Min Act: -0.0000

Data Index: 105811 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.5132. Min Act: -0.0000

Data Index: 392797 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.5480. Min Act: -0.0000

Data Index: 100633 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.5262. Min Act: -0.0000

Data Index: 1069524 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1276445 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.5143. Min Act: -0.0000

Data Index: 23223 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.5288. Min Act: -0.0000

Data Index: 835754 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.6057. Min Act: -0.0000

Data Index: 582308 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1231820 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1109636 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.4890. Min Act: -0.0000

Data Index: 92475 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1359558 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1142878 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 0.6848. Min Range: -0.6848

Max Act: 0.5182. Min Act: -0.0000

Data Index: 82793 (C4 (Web Text))

Max Activating Token Index: 692