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

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

Neuron 3486 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: 0.2414. Min Range: -0.2414

Max Act: 0.2414. Min Act: -0.0000

Data Index: 857887 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1168358 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2294. Min Act: -0.0000

Data Index: 1193515 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2210. Min Act: -0.0000

Data Index: 160731 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1160219 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2126. Min Act: -0.0000

Data Index: 298475 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2078. Min Act: -0.0001

Data Index: 921760 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2067. Min Act: -0.0000

Data Index: 40566 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1323406 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1097392 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1998. Min Act: -0.0000

Data Index: 129096 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1236909 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1814. Min Act: -0.0001

Data Index: 615910 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1883. Min Act: -0.0000

Data Index: 711699 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1824. Min Act: -0.0001

Data Index: 1195205 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1804. Min Act: -0.0000

Data Index: 1095486 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1746. Min Act: -0.0000

Data Index: 13506 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1727. Min Act: -0.0000

Data Index: 97782 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1840. Min Act: -0.0000

Data Index: 412175 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 0.2414. Min Range: -0.2414

Max Act: 0.1622. Min Act: -0.0000

Data Index: 100766 (C4 (Web Text))

Max Activating Token Index: 662