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

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

Neuron 3967 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.5373. Min Act: -0.0000

Data Index: 1142678 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.5821. Min Act: -0.0000

Data Index: 717608 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.5200. Min Act: -0.0000

Data Index: 23296 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.4797. Min Act: -0.0000

Data Index: 674548 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.3717. Min Act: -0.0000

Data Index: 886230 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.2141. Min Act: -0.0000

Data Index: 657884 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.2117. Min Act: -0.0001

Data Index: 444872 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.0757. Min Act: -0.0000

Data Index: 749681 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.0705. Min Act: -0.0000

Data Index: 798004 (C4 (Web Text))

Max Activating Token Index: 614

Text #9

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.0694. Min Act: -0.0000

Data Index: 567650 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.2106. Min Act: -0.0000

Data Index: 992108 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.1382. Min Act: -0.0000

Data Index: 1220483 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.1635. Min Act: -0.0000

Data Index: 657673 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.1304. Min Act: -0.0000

Data Index: 445768 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.1005. Min Act: -0.0000

Data Index: 886833 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.0611. Min Act: -0.0000

Data Index: 825113 (C4 (Web Text))

Max Activating Token Index: 934

Text #16

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.0358. Min Act: -0.0000

Data Index: 61170 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.0877. Min Act: -0.0000

Data Index: 725384 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.0509. Min Act: -0.0000

Data Index: 1079870 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 1.5821. Min Range: -1.5821

Max Act: 1.1342. Min Act: -0.0000

Data Index: 50913 (C4 (Web Text))

Max Activating Token Index: 608