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

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

Neuron 4585 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1796. Min Range: -1.1796

Max Act: 1.1796. Min Act: -0.0000

Data Index: 709954 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.9554. Min Act: 0.0000

Data Index: 1225556 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.7426. Min Act: -0.0000

Data Index: 399934 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.7077. Min Act: 0.0000

Data Index: 95132 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.6755. Min Act: 0.0000

Data Index: 1069759 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.6790. Min Act: -0.0000

Data Index: 809752 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.6781. Min Act: 0.0000

Data Index: 247343 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.6540. Min Act: -0.0000

Data Index: 719217 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.6118. Min Act: 0.0000

Data Index: 97479 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.6363. Min Act: -0.0000

Data Index: 735611 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.6304. Min Act: -0.0000

Data Index: 510514 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1246168 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.6373. Min Act: 0.0000

Data Index: 1268297 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.6014. Min Act: -0.0000

Data Index: 298727 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.6361. Min Act: 0.0000

Data Index: 1006644 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.6183. Min Act: -0.0000

Data Index: 250095 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.5930. Min Act: 0.0001

Data Index: 182803 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.5931. Min Act: -0.0000

Data Index: 802067 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1053771 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 1.1796. Min Range: -1.1796

Max Act: 0.5766. Min Act: 0.0004

Data Index: 14426 (C4 (Web Text))

Max Activating Token Index: 168