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

Dataset: The Pile

Neuron 4617 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2284. Min Range: -1.2284

Max Act: 1.2284. Min Act: -0.0000

Data Index: 488265 (The Pile)

Max Activating Token Index: 78

Text #1

Max Range: 1.2284. Min Range: -1.2284

Max Act: 1.1623. Min Act: -0.0000

Data Index: 665060 (The Pile)

Max Activating Token Index: 27

Text #2

Max Range: 1.2284. Min Range: -1.2284

Max Act: 1.0855. Min Act: -0.0000

Data Index: 1007314 (The Pile)

Max Activating Token Index: 537

Text #3

Max Range: 1.2284. Min Range: -1.2284

Max Act: 1.0503. Min Act: -0.0000

Data Index: 1604770 (The Pile)

Max Activating Token Index: 927

Text #4

Max Range: 1.2284. Min Range: -1.2284

Max Act: 1.0454. Min Act: -0.0000

Data Index: 249423 (The Pile)

Max Activating Token Index: 624

Text #5

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9605. Min Act: -0.0000

Data Index: 582587 (The Pile)

Max Activating Token Index: 182

Text #6

Max Range: 1.2284. Min Range: -1.2284

Max Act: 1.0269. Min Act: -0.0000

Data Index: 1464550 (The Pile)

Max Activating Token Index: 695

Text #7

Max Range: 1.2284. Min Range: -1.2284

Max Act: 1.0115. Min Act: -0.0000

Data Index: 281231 (The Pile)

Max Activating Token Index: 578

Text #8

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9908. Min Act: 0.0000

Data Index: 1555436 (The Pile)

Max Activating Token Index: 148

Text #9

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9836. Min Act: -0.0000

Data Index: 1146488 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 1.2284. Min Range: -1.2284

Max Act: 1.0075. Min Act: -0.0000

Data Index: 590584 (The Pile)

Max Activating Token Index: 968

Text #11

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9039. Min Act: -0.0000

Data Index: 706369 (The Pile)

Max Activating Token Index: 625

Text #12

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9424. Min Act: 0.0000

Data Index: 991374 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 1.2284. Min Range: -1.2284

Max Act: 1.0083. Min Act: -0.0000

Data Index: 367576 (The Pile)

Max Activating Token Index: 51

Text #14

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9273. Min Act: -0.0000

Data Index: 770287 (The Pile)

Max Activating Token Index: 100

Text #15

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.8695. Min Act: -0.0000

Data Index: 733889 (The Pile)

Max Activating Token Index: 231

Text #16

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9134. Min Act: -0.0000

Data Index: 1974115 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9630. Min Act: -0.0000

Data Index: 567047 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1046652 (The Pile)

Max Activating Token Index: 262

Text #19

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.8996. Min Act: -0.0000

Data Index: 410031 (The Pile)

Max Activating Token Index: 605