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

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

Neuron 3628 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: 3.1097. Min Range: -3.1097

Max Act: 3.1097. Min Act: -0.0000

Data Index: 258430 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.5561. Min Act: -0.0000

Data Index: 958478 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.6672. Min Act: -0.0000

Data Index: 694690 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.3392. Min Act: -0.0000

Data Index: 1332822 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.4636. Min Act: -0.0000

Data Index: 354786 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.3055. Min Act: -0.0000

Data Index: 1010751 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.2266. Min Act: -0.0001

Data Index: 144784 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.2774. Min Act: -0.0000

Data Index: 624041 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.1400. Min Act: -0.0001

Data Index: 542751 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.2557. Min Act: -0.0000

Data Index: 936592 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.1068. Min Act: -0.0001

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.0742. Min Act: -0.0000

Data Index: 363161 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.1973. Min Act: -0.0000

Data Index: 867324 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.1811. Min Act: -0.0000

Data Index: 646772 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.0395. Min Act: -0.0000

Data Index: 1268705 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.0268. Min Act: -0.0000

Data Index: 599062 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.2181. Min Act: -0.0000

Data Index: 1325784 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 3.1097. Min Range: -3.1097

Max Act: 1.9984. Min Act: -0.0000

Data Index: 1312302 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 3.1097. Min Range: -3.1097

Max Act: 2.1047. Min Act: -0.0000

Data Index: 905338 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 3.1097. Min Range: -3.1097

Max Act: 1.9951. Min Act: -0.0000

Data Index: 650860 (C4 (Web Text))

Max Activating Token Index: 730