Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 559 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.9258. Min Act: -0.0000

Data Index: 1614997 (The Pile)

Max Activating Token Index: 559

Text #1

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.8093. Min Act: -0.0000

Data Index: 1671058 (The Pile)

Max Activating Token Index: 373

Text #2

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.7745. Min Act: -0.0000

Data Index: 1639413 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.6463. Min Act: -0.0000

Data Index: 1100885 (The Pile)

Max Activating Token Index: 229

Text #4

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.6839. Min Act: -0.0000

Data Index: 775207 (The Pile)

Max Activating Token Index: 216

Text #5

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.5782. Min Act: -0.0000

Data Index: 1246710 (The Pile)

Max Activating Token Index: 438

Text #6

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.6787. Min Act: -0.0000

Data Index: 1348184 (The Pile)

Max Activating Token Index: 329

Text #7

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.3717. Min Act: -0.0000

Data Index: 124996 (The Pile)

Max Activating Token Index: 841

Text #8

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.5013. Min Act: -0.0000

Data Index: 1517314 (The Pile)

Max Activating Token Index: 142

Text #9

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.6661. Min Act: -0.0000

Data Index: 795838 (The Pile)

Max Activating Token Index: 779

Text #10

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.4101. Min Act: -0.0000

Data Index: 92372 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.5592. Min Act: -0.0000

Data Index: 400782 (The Pile)

Max Activating Token Index: 83

Text #12

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.5588. Min Act: -0.0000

Data Index: 762188 (The Pile)

Max Activating Token Index: 611

Text #13

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.6122. Min Act: -0.0000

Data Index: 1817686 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.5172. Min Act: -0.0000

Data Index: 1108096 (The Pile)

Max Activating Token Index: 582

Text #15

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.4176. Min Act: -0.0000

Data Index: 1095374 (The Pile)

Max Activating Token Index: 307

Text #16

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.4141. Min Act: -0.0000

Data Index: 498083 (The Pile)

Max Activating Token Index: 492

Text #17

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.4765. Min Act: -0.0000

Data Index: 1189095 (The Pile)

Max Activating Token Index: 703

Text #18

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.4715. Min Act: -0.0000

Data Index: 1339240 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 1.9258. Min Range: -1.9258

Max Act: 1.5459. Min Act: -0.0000

Data Index: 870485 (The Pile)

Max Activating Token Index: 496