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

Dataset: The Pile

Neuron 3511 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: 0.5081. Min Range: -0.5081

Max Act: 0.5081. Min Act: -0.0000

Data Index: 37478 (The Pile)

Max Activating Token Index: 663

Text #1

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1452513 (The Pile)

Max Activating Token Index: 234

Text #2

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.4398. Min Act: -0.0000

Data Index: 85755 (The Pile)

Max Activating Token Index: 282

Text #3

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.4552. Min Act: -0.0000

Data Index: 1547997 (The Pile)

Max Activating Token Index: 655

Text #4

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.4415. Min Act: -0.0000

Data Index: 372215 (The Pile)

Max Activating Token Index: 380

Text #5

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1743941 (The Pile)

Max Activating Token Index: 726

Text #6

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.4247. Min Act: -0.0000

Data Index: 1612681 (The Pile)

Max Activating Token Index: 52

Text #7

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.4109. Min Act: -0.0000

Data Index: 1113797 (The Pile)

Max Activating Token Index: 519

Text #8

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.4292. Min Act: -0.0000

Data Index: 213349 (The Pile)

Max Activating Token Index: 398

Text #9

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3984. Min Act: -0.0000

Data Index: 439549 (The Pile)

Max Activating Token Index: 186

Text #10

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3894. Min Act: -0.0000

Data Index: 14924 (The Pile)

Max Activating Token Index: 760

Text #11

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1304822 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3848. Min Act: -0.0000

Data Index: 1386113 (The Pile)

Max Activating Token Index: 74

Text #13

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3965. Min Act: -0.0000

Data Index: 731841 (The Pile)

Max Activating Token Index: 723

Text #14

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3651. Min Act: -0.0000

Data Index: 1615220 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3739. Min Act: -0.0000

Data Index: 932210 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3750. Min Act: -0.0000

Data Index: 1285981 (The Pile)

Max Activating Token Index: 403

Text #17

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3699. Min Act: -0.0000

Data Index: 463306 (The Pile)

Max Activating Token Index: 655

Text #18

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3879. Min Act: -0.0000

Data Index: 148245 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 0.5081. Min Range: -0.5081

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1579593 (The Pile)

Max Activating Token Index: 586