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

Dataset: The Pile

Neuron 2371 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.6043. Min Act: -0.0000

Data Index: 535560 (The Pile)

Max Activating Token Index: 625

Text #1

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.5427. Min Act: -0.0000

Data Index: 1366658 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.5756. Min Act: -0.0001

Data Index: 448996 (The Pile)

Max Activating Token Index: 156

Text #3

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.4774. Min Act: -0.0000

Data Index: 1217312 (The Pile)

Max Activating Token Index: 349

Text #4

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.3729. Min Act: -0.0000

Data Index: 1925641 (The Pile)

Max Activating Token Index: 128

Text #5

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.4627. Min Act: -0.0000

Data Index: 1864636 (The Pile)

Max Activating Token Index: 183

Text #6

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.5141. Min Act: -0.0001

Data Index: 92009 (The Pile)

Max Activating Token Index: 127

Text #7

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.4228. Min Act: -0.0000

Data Index: 1511989 (The Pile)

Max Activating Token Index: 218

Text #8

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.3281. Min Act: -0.0000

Data Index: 138958 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.3481. Min Act: -0.0000

Data Index: 1681870 (The Pile)

Max Activating Token Index: 327

Text #10

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.2916. Min Act: -0.0000

Data Index: 1904678 (The Pile)

Max Activating Token Index: 330

Text #11

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.4125. Min Act: -0.0000

Data Index: 335345 (The Pile)

Max Activating Token Index: 122

Text #12

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.4241. Min Act: -0.0000

Data Index: 531668 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.3272. Min Act: -0.0000

Data Index: 1740001 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.3406. Min Act: -0.0000

Data Index: 1447544 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.1953. Min Act: -0.0000

Data Index: 897812 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.1099. Min Act: -0.0000

Data Index: 389067 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.2363. Min Act: -0.0000

Data Index: 969345 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.2012. Min Act: -0.0000

Data Index: 564195 (The Pile)

Max Activating Token Index: 350

Text #19

Max Range: 1.6043. Min Range: -1.6043

Max Act: 1.1264. Min Act: -0.0000

Data Index: 1255261 (The Pile)

Max Activating Token Index: 380