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

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

Neuron 1161 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.4696. Min Act: -0.0000

Data Index: 1241754 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.2013. Min Act: -0.0000

Data Index: 210496 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.1192. Min Act: -0.0000

Data Index: 411686 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.2599. Min Act: -0.0000

Data Index: 987728 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.1998. Min Act: -0.0000

Data Index: 1116614 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.1679. Min Act: -0.0000

Data Index: 1089369 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.1588. Min Act: -0.0000

Data Index: 901991 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.2139. Min Act: -0.0000

Data Index: 831959 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.1738. Min Act: -0.0000

Data Index: 135170 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.1744. Min Act: -0.0000

Data Index: 640085 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.1148. Min Act: -0.0000

Data Index: 145049 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.1095. Min Act: -0.0000

Data Index: 544875 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.1063. Min Act: -0.0000

Data Index: 1169270 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.0421. Min Act: -0.0000

Data Index: 748988 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1196840 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.0208. Min Act: -0.0000

Data Index: 175843 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.0803. Min Act: -0.0000

Data Index: 116170 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.1381. Min Act: -0.0000

Data Index: 61206 (C4 (Web Text))

Max Activating Token Index: 842

Text #18

Max Range: 1.4696. Min Range: -1.4696

Max Act: 1.1376. Min Act: -0.0000

Data Index: 1263487 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 1.4696. Min Range: -1.4696

Max Act: 0.9997. Min Act: -0.0000

Data Index: 755289 (C4 (Web Text))

Max Activating Token Index: 665