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

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

Neuron 940 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2698. Min Act: -0.0003

Data Index: 1253785 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2470. Min Act: -0.0003

Data Index: 279739 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2571. Min Act: -0.0003

Data Index: 55210 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2029. Min Act: -0.0003

Data Index: 24021 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2151. Min Act: -0.0003

Data Index: 644259 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2196. Min Act: -0.0003

Data Index: 765045 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2111. Min Act: -0.0003

Data Index: 428535 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2112. Min Act: -0.0003

Data Index: 1188829 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1967. Min Act: -0.0003

Data Index: 1363163 (Python Code)

Max Activating Token Index: 610

Text #9

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2017. Min Act: -0.0003

Data Index: 298207 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2092. Min Act: -0.0003

Data Index: 1465790 (Python Code)

Max Activating Token Index: 793

Text #11

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2088. Min Act: -0.0003

Data Index: 1622457 (Python Code)

Max Activating Token Index: 495

Text #12

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2066. Min Act: -0.0003

Data Index: 1535591 (Python Code)

Max Activating Token Index: 314

Text #13

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2033. Min Act: -0.0003

Data Index: 1058961 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2044. Min Act: -0.0003

Data Index: 723145 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1964. Min Act: -0.0003

Data Index: 1164974 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.2083. Min Act: -0.0003

Data Index: 426465 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1939. Min Act: -0.0003

Data Index: 1570620 (Python Code)

Max Activating Token Index: 588

Text #18

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1992. Min Act: -0.0004

Data Index: 1638459 (Python Code)

Max Activating Token Index: 199

Text #19

Max Range: 0.2698. Min Range: -0.2698

Max Act: 0.1988. Min Act: -0.0003

Data Index: 100795 (C4 (Web Text))

Max Activating Token Index: 12