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

Dataset: The Pile

Neuron 946 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1828851 (The Pile)

Max Activating Token Index: 460

Text #1

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2397. Min Act: -0.0000

Data Index: 569336 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2172. Min Act: -0.0000

Data Index: 450319 (The Pile)

Max Activating Token Index: 532

Text #3

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2402. Min Act: -0.0000

Data Index: 1791959 (The Pile)

Max Activating Token Index: 209

Text #4

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2324. Min Act: -0.0000

Data Index: 1498737 (The Pile)

Max Activating Token Index: 29

Text #5

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2273. Min Act: -0.0000

Data Index: 301742 (The Pile)

Max Activating Token Index: 200

Text #6

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2026. Min Act: -0.0000

Data Index: 1580327 (The Pile)

Max Activating Token Index: 704

Text #7

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1719377 (The Pile)

Max Activating Token Index: 110

Text #8

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2130. Min Act: -0.0000

Data Index: 544706 (The Pile)

Max Activating Token Index: 98

Text #9

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2338. Min Act: -0.0000

Data Index: 1615459 (The Pile)

Max Activating Token Index: 658

Text #10

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2200. Min Act: -0.0000

Data Index: 766377 (The Pile)

Max Activating Token Index: 978

Text #11

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1502284 (The Pile)

Max Activating Token Index: 247

Text #12

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2162. Min Act: -0.0000

Data Index: 1103466 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1608777 (The Pile)

Max Activating Token Index: 167

Text #14

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1760953 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2190. Min Act: -0.0000

Data Index: 634623 (The Pile)

Max Activating Token Index: 754

Text #16

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1000774 (The Pile)

Max Activating Token Index: 313

Text #17

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1028210 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2092. Min Act: -0.0000

Data Index: 325660 (The Pile)

Max Activating Token Index: 282

Text #19

Max Range: 0.2610. Min Range: -0.2610

Max Act: 0.2074. Min Act: -0.0000

Data Index: 848438 (The Pile)

Max Activating Token Index: 689