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

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

Neuron 257 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: 0.8753. Min Range: -0.8753

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1000042 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1171253 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1213506 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1125087 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.7611. Min Act: -0.0000

Data Index: 1123842 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1104773 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.7761. Min Act: -0.0000

Data Index: 639724 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.7860. Min Act: -0.0000

Data Index: 171238 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.6986. Min Act: -0.0000

Data Index: 830065 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.6899. Min Act: -0.0000

Data Index: 629844 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.7657. Min Act: -0.0000

Data Index: 185776 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.6922. Min Act: -0.0000

Data Index: 881100 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.6284. Min Act: -0.0000

Data Index: 129239 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1020776 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.6831. Min Act: -0.0000

Data Index: 77688 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.6807. Min Act: -0.0000

Data Index: 740871 (C4 (Web Text))

Max Activating Token Index: 5

Text #16

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.7230. Min Act: -0.0000

Data Index: 857302 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.6867. Min Act: -0.0000

Data Index: 382823 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.7010. Min Act: -0.0000

Data Index: 350438 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.8753. Min Range: -0.8753

Max Act: 0.7175. Min Act: -0.0000

Data Index: 563558 (C4 (Web Text))

Max Activating Token Index: 320