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

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

Neuron 760 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0932. Min Act: -0.0000

Data Index: 696328 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0879. Min Act: -0.0000

Data Index: 984521 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0946. Min Act: -0.0000

Data Index: 388340 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0852. Min Act: -0.0000

Data Index: 702689 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0802. Min Act: -0.0000

Data Index: 629123 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0787. Min Act: -0.0000

Data Index: 654863 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0751. Min Act: -0.0000

Data Index: 833500 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0747. Min Act: -0.0000

Data Index: 708847 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0739. Min Act: -0.0000

Data Index: 4412 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0716. Min Act: -0.0000

Data Index: 217519 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0727. Min Act: -0.0000

Data Index: 798835 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0735. Min Act: -0.0000

Data Index: 1237533 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0687. Min Act: -0.0000

Data Index: 350167 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0713. Min Act: -0.0000

Data Index: 124455 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0657. Min Act: -0.0000

Data Index: 235677 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0673. Min Act: -0.0000

Data Index: 1226079 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0656. Min Act: -0.0000

Data Index: 1026839 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0614. Min Act: -0.0000

Data Index: 1101907 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0685. Min Act: -0.0000

Data Index: 1276988 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 0.0946. Min Range: -0.0946

Max Act: 0.0646. Min Act: -0.0000

Data Index: 76179 (C4 (Web Text))

Max Activating Token Index: 904