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

Dataset: The Pile

Neuron 3870 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6388. Min Act: -0.0000

Data Index: 945017 (The Pile)

Max Activating Token Index: 621

Text #1

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6231. Min Act: -0.0000

Data Index: 596241 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6252. Min Act: -0.0000

Data Index: 976094 (The Pile)

Max Activating Token Index: 551

Text #3

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.7161. Min Act: -0.0000

Data Index: 578752 (The Pile)

Max Activating Token Index: 911

Text #4

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1126919 (The Pile)

Max Activating Token Index: 500

Text #5

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1273490 (The Pile)

Max Activating Token Index: 425

Text #6

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5600. Min Act: -0.0000

Data Index: 910698 (The Pile)

Max Activating Token Index: 1014

Text #7

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1626171 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.6120. Min Act: -0.0000

Data Index: 451906 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5054. Min Act: -0.0000

Data Index: 185756 (The Pile)

Max Activating Token Index: 294

Text #10

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.4580. Min Act: -0.0000

Data Index: 1281509 (The Pile)

Max Activating Token Index: 339

Text #11

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.4889. Min Act: -0.0000

Data Index: 31344 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1055595 (The Pile)

Max Activating Token Index: 551

Text #13

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.4998. Min Act: -0.0000

Data Index: 184406 (The Pile)

Max Activating Token Index: 778

Text #14

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1469408 (The Pile)

Max Activating Token Index: 769

Text #15

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1599799 (The Pile)

Max Activating Token Index: 284

Text #16

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.4833. Min Act: -0.0000

Data Index: 221487 (The Pile)

Max Activating Token Index: 714

Text #17

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.4220. Min Act: -0.0000

Data Index: 176080 (The Pile)

Max Activating Token Index: 917

Text #18

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.5203. Min Act: -0.0000

Data Index: 990558 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 0.7161. Min Range: -0.7161

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1892639 (The Pile)

Max Activating Token Index: 316