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

Dataset: The Pile

Neuron 4216 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.5141. Min Act: -0.0000

Data Index: 411965 (The Pile)

Max Activating Token Index: 308

Text #1

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4177. Min Act: -0.0000

Data Index: 1898857 (The Pile)

Max Activating Token Index: 752

Text #2

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.4129. Min Act: -0.0000

Data Index: 362252 (The Pile)

Max Activating Token Index: 428

Text #3

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.2867. Min Act: -0.0000

Data Index: 1966089 (The Pile)

Max Activating Token Index: 421

Text #4

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.3532. Min Act: -0.0000

Data Index: 1040213 (The Pile)

Max Activating Token Index: 605

Text #5

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.3945. Min Act: -0.0000

Data Index: 605591 (The Pile)

Max Activating Token Index: 550

Text #6

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.1722. Min Act: -0.0000

Data Index: 1253991 (The Pile)

Max Activating Token Index: 700

Text #7

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.3910. Min Act: -0.0000

Data Index: 1560752 (The Pile)

Max Activating Token Index: 306

Text #8

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.1579. Min Act: -0.0000

Data Index: 811484 (The Pile)

Max Activating Token Index: 150

Text #9

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.0739. Min Act: -0.0000

Data Index: 1276058 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.2007. Min Act: -0.0000

Data Index: 1642053 (The Pile)

Max Activating Token Index: 769

Text #11

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.1007. Min Act: -0.0000

Data Index: 1479308 (The Pile)

Max Activating Token Index: 281

Text #12

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.1599. Min Act: -0.0000

Data Index: 1457673 (The Pile)

Max Activating Token Index: 967

Text #13

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.0552. Min Act: -0.0000

Data Index: 1044165 (The Pile)

Max Activating Token Index: 485

Text #14

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.0872. Min Act: -0.0000

Data Index: 1106941 (The Pile)

Max Activating Token Index: 379

Text #15

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.0932. Min Act: -0.0000

Data Index: 904138 (The Pile)

Max Activating Token Index: 126

Text #16

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.1160. Min Act: -0.0000

Data Index: 1967307 (The Pile)

Max Activating Token Index: 52

Text #17

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.1729. Min Act: -0.0000

Data Index: 1640821 (The Pile)

Max Activating Token Index: 225

Text #18

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.0120. Min Act: -0.0000

Data Index: 306986 (The Pile)

Max Activating Token Index: 100

Text #19

Max Range: 1.5141. Min Range: -1.5141

Max Act: 1.0350. Min Act: -0.0000

Data Index: 843044 (The Pile)

Max Activating Token Index: 569