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

Dataset: The Pile

Neuron 2173 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: 0.6267. Min Range: -0.6267

Max Act: 0.6093. Min Act: -0.0000

Data Index: 1142066 (The Pile)

Max Activating Token Index: 855

Text #1

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.6110. Min Act: -0.0000

Data Index: 1851332 (The Pile)

Max Activating Token Index: 565

Text #2

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1991276 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.6207. Min Act: -0.0000

Data Index: 751799 (The Pile)

Max Activating Token Index: 762

Text #4

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5913. Min Act: -0.0000

Data Index: 4833 (The Pile)

Max Activating Token Index: 913

Text #5

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1369542 (The Pile)

Max Activating Token Index: 390

Text #6

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5851. Min Act: -0.0000

Data Index: 1461263 (The Pile)

Max Activating Token Index: 256

Text #7

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.6267. Min Act: -0.0000

Data Index: 1267468 (The Pile)

Max Activating Token Index: 126

Text #8

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5760. Min Act: -0.0000

Data Index: 59330 (The Pile)

Max Activating Token Index: 1009

Text #9

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5736. Min Act: -0.0000

Data Index: 744578 (The Pile)

Max Activating Token Index: 102

Text #10

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1446523 (The Pile)

Max Activating Token Index: 541

Text #11

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5279. Min Act: -0.0000

Data Index: 1587604 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1514403 (The Pile)

Max Activating Token Index: 424

Text #13

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5282. Min Act: -0.0000

Data Index: 653881 (The Pile)

Max Activating Token Index: 524

Text #14

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1262742 (The Pile)

Max Activating Token Index: 314

Text #15

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1417013 (The Pile)

Max Activating Token Index: 629

Text #16

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1768656 (The Pile)

Max Activating Token Index: 917

Text #17

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5457. Min Act: -0.0000

Data Index: 747073 (The Pile)

Max Activating Token Index: 117

Text #18

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1799763 (The Pile)

Max Activating Token Index: 362

Text #19

Max Range: 0.6267. Min Range: -0.6267

Max Act: 0.5183. Min Act: -0.0000

Data Index: 112023 (The Pile)

Max Activating Token Index: 416