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

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

Neuron 1619 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: 0.8566. Min Range: -0.8566

Max Act: 0.8127. Min Act: -0.0001

Data Index: 1359278 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7771. Min Act: -0.0001

Data Index: 1552739 (Python Code)

Max Activating Token Index: 708

Text #2

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.8566. Min Act: -0.0001

Data Index: 928769 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7828. Min Act: -0.0001

Data Index: 783191 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7378. Min Act: -0.0001

Data Index: 939350 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7687. Min Act: -0.0001

Data Index: 1200902 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7266. Min Act: -0.0001

Data Index: 106866 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.8030. Min Act: -0.0001

Data Index: 773559 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.8019. Min Act: -0.0000

Data Index: 311304 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.8088. Min Act: -0.0001

Data Index: 121281 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7451. Min Act: -0.0001

Data Index: 172901 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6900. Min Act: -0.0001

Data Index: 823281 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7672. Min Act: -0.0001

Data Index: 465952 (C4 (Web Text))

Max Activating Token Index: 616

Text #13

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7294. Min Act: -0.0001

Data Index: 1366154 (Python Code)

Max Activating Token Index: 117

Text #14

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1251827 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6993. Min Act: -0.0001

Data Index: 259264 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.6787. Min Act: -0.0001

Data Index: 616706 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7561. Min Act: -0.0001

Data Index: 1065714 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7125. Min Act: -0.0001

Data Index: 1021501 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.8566. Min Range: -0.8566

Max Act: 0.7117. Min Act: -0.0001

Data Index: 1371423 (Python Code)

Max Activating Token Index: 577