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

Dataset: The Pile

Neuron 768 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: 1.3201. Min Range: -1.3201

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1865741 (The Pile)

Max Activating Token Index: 675

Text #1

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.3201. Min Act: -0.0000

Data Index: 194740 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.2343. Min Act: -0.0000

Data Index: 1767796 (The Pile)

Max Activating Token Index: 416

Text #3

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.2254. Min Act: -0.0000

Data Index: 30387 (The Pile)

Max Activating Token Index: 989

Text #4

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.2685. Min Act: -0.0000

Data Index: 1589056 (The Pile)

Max Activating Token Index: 62

Text #5

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1127508 (The Pile)

Max Activating Token Index: 161

Text #6

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.1007. Min Act: 0.0000

Data Index: 1352257 (The Pile)

Max Activating Token Index: 444

Text #7

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.0994. Min Act: -0.0000

Data Index: 1900354 (The Pile)

Max Activating Token Index: 628

Text #8

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.1162. Min Act: -0.0000

Data Index: 290956 (The Pile)

Max Activating Token Index: 814

Text #9

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.1366. Min Act: -0.0000

Data Index: 282119 (The Pile)

Max Activating Token Index: 444

Text #10

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.0734. Min Act: -0.0000

Data Index: 494808 (The Pile)

Max Activating Token Index: 894

Text #11

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.1300. Min Act: -0.0000

Data Index: 1960704 (The Pile)

Max Activating Token Index: 612

Text #12

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.1052. Min Act: -0.0000

Data Index: 1905967 (The Pile)

Max Activating Token Index: 482

Text #13

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.0695. Min Act: -0.0000

Data Index: 1178758 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.0574. Min Act: -0.0000

Data Index: 564860 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.0177. Min Act: -0.0000

Data Index: 922703 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.0969. Min Act: -0.0000

Data Index: 208237 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.0263. Min Act: -0.0000

Data Index: 1250715 (The Pile)

Max Activating Token Index: 760

Text #18

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.0586. Min Act: -0.0000

Data Index: 1730830 (The Pile)

Max Activating Token Index: 149

Text #19

Max Range: 1.3201. Min Range: -1.3201

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1789617 (The Pile)

Max Activating Token Index: 437