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

Dataset: The Pile

Neuron 1957 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.4195. Min Act: -0.0000

Data Index: 1090788 (The Pile)

Max Activating Token Index: 942

Text #1

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3463. Min Act: -0.0000

Data Index: 1997614 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3150. Min Act: 0.0001

Data Index: 1467794 (The Pile)

Max Activating Token Index: 656

Text #3

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.3103. Min Act: -0.0000

Data Index: 1239855 (The Pile)

Max Activating Token Index: 477

Text #4

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.2613. Min Act: 0.0000

Data Index: 200273 (The Pile)

Max Activating Token Index: 782

Text #5

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.1545. Min Act: -0.0000

Data Index: 1207936 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.1658. Min Act: 0.0000

Data Index: 1364477 (The Pile)

Max Activating Token Index: 812

Text #7

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.1119. Min Act: -0.0000

Data Index: 1526633 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.0775. Min Act: -0.0000

Data Index: 1779982 (The Pile)

Max Activating Token Index: 342

Text #9

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.1001. Min Act: -0.0000

Data Index: 1077074 (The Pile)

Max Activating Token Index: 770

Text #10

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.0179. Min Act: 0.0000

Data Index: 314446 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.0599. Min Act: 0.0000

Data Index: 1316302 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 1.4195. Min Range: -1.4195

Max Act: 0.9990. Min Act: 0.0000

Data Index: 1302907 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.0522. Min Act: -0.0000

Data Index: 1213543 (The Pile)

Max Activating Token Index: 933

Text #14

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.0657. Min Act: 0.0000

Data Index: 976989 (The Pile)

Max Activating Token Index: 541

Text #15

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.0510. Min Act: -0.0000

Data Index: 284761 (The Pile)

Max Activating Token Index: 1004

Text #16

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.0508. Min Act: -0.0000

Data Index: 1682471 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 1.4195. Min Range: -1.4195

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1210487 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 1.4195. Min Range: -1.4195

Max Act: 1.0680. Min Act: 0.0000

Data Index: 758384 (The Pile)

Max Activating Token Index: 1014

Text #19

Max Range: 1.4195. Min Range: -1.4195

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1140590 (The Pile)

Max Activating Token Index: 786