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

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

Neuron 799 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.5625. Min Act: -0.0001

Data Index: 586835 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.5015. Min Act: -0.0000

Data Index: 155471 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.5736. Min Act: -0.0000

Data Index: 583232 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.1964. Min Act: -0.0001

Data Index: 824711 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.1725. Min Act: 0.0000

Data Index: 1290893 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.3049. Min Act: -0.0000

Data Index: 927727 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.0496. Min Act: -0.0000

Data Index: 1380810 (Python Code)

Max Activating Token Index: 312

Text #7

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1069898 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 1.5736. Min Range: -1.5736

Max Act: 0.9921. Min Act: -0.0001

Data Index: 625964 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 1.5736. Min Range: -1.5736

Max Act: 1.0780. Min Act: -0.0001

Data Index: 36598 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 1.5736. Min Range: -1.5736

Max Act: 0.9766. Min Act: -0.0001

Data Index: 1062001 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.5736. Min Range: -1.5736

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1046852 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 1.5736. Min Range: -1.5736

Max Act: 0.9165. Min Act: -0.0000

Data Index: 22984 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 1.5736. Min Range: -1.5736

Max Act: 0.8564. Min Act: -0.0001

Data Index: 857527 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 1.5736. Min Range: -1.5736

Max Act: 0.7501. Min Act: -0.0000

Data Index: 1567117 (Python Code)

Max Activating Token Index: 828

Text #15

Max Range: 1.5736. Min Range: -1.5736

Max Act: 0.8713. Min Act: 0.0000

Data Index: 1125771 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 1.5736. Min Range: -1.5736

Max Act: 0.7901. Min Act: -0.0001

Data Index: 1164826 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 1.5736. Min Range: -1.5736

Max Act: 0.6282. Min Act: -0.0001

Data Index: 719299 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 1.5736. Min Range: -1.5736

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1192943 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 1.5736. Min Range: -1.5736

Max Act: 0.7881. Min Act: 0.0000

Data Index: 1243903 (C4 (Web Text))

Max Activating Token Index: 598