Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 93 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1675. Min Act: -0.0001

Data Index: 879071 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1330671 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1263. Min Act: -0.0001

Data Index: 325898 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1059. Min Act: -0.0001

Data Index: 273291 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.1101. Min Act: -0.0001

Data Index: 1031510 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0981. Min Act: -0.0001

Data Index: 2421 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0879. Min Act: -0.0001

Data Index: 93584 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0935. Min Act: -0.0001

Data Index: 854970 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0861. Min Act: -0.0001

Data Index: 613162 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0964. Min Act: -0.0001

Data Index: 477242 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0874. Min Act: -0.0001

Data Index: 508155 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0929. Min Act: -0.0001

Data Index: 85566 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0833. Min Act: -0.0001

Data Index: 153072 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0793. Min Act: -0.0001

Data Index: 646258 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0798. Min Act: -0.0001

Data Index: 782499 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0763. Min Act: -0.0001

Data Index: 873797 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0823. Min Act: -0.0001

Data Index: 106602 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0815. Min Act: -0.0001

Data Index: 405622 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0784. Min Act: -0.0001

Data Index: 294891 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.1675. Min Range: -0.1675

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1137218 (C4 (Web Text))

Max Activating Token Index: 476