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

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

Neuron 1772 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.8018. Min Act: -0.0000

Data Index: 1267493 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.7324. Min Act: -0.0000

Data Index: 319266 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6804. Min Act: -0.0000

Data Index: 272121 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6558. Min Act: -0.0000

Data Index: 427315 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6209. Min Act: 0.0000

Data Index: 359119 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.6377. Min Act: -0.0000

Data Index: 166475 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5821. Min Act: 0.0001

Data Index: 708787 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5633. Min Act: -0.0000

Data Index: 287405 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5437. Min Act: -0.0000

Data Index: 128453 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5675. Min Act: -0.0000

Data Index: 540696 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5631. Min Act: -0.0000

Data Index: 495810 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5639. Min Act: -0.0000

Data Index: 828550 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5079. Min Act: -0.0000

Data Index: 769877 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1262539 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1090646 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5627. Min Act: 0.0000

Data Index: 647498 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5395. Min Act: -0.0000

Data Index: 725571 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5112. Min Act: -0.0000

Data Index: 460328 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.4921. Min Act: 0.0001

Data Index: 768972 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.8018. Min Range: -0.8018

Max Act: 0.5169. Min Act: -0.0000

Data Index: 250448 (C4 (Web Text))

Max Activating Token Index: 117