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

Dataset: The Pile

Neuron 255 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: 0.5745. Min Range: -0.5745

Max Act: 0.5745. Min Act: -0.0000

Data Index: 919143 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1452303 (The Pile)

Max Activating Token Index: 675

Text #2

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.5108. Min Act: -0.0000

Data Index: 743639 (The Pile)

Max Activating Token Index: 718

Text #3

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1953573 (The Pile)

Max Activating Token Index: 484

Text #4

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4721. Min Act: 0.0000

Data Index: 1233461 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4521. Min Act: -0.0000

Data Index: 804537 (The Pile)

Max Activating Token Index: 862

Text #6

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1984600 (The Pile)

Max Activating Token Index: 281

Text #7

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1160333 (The Pile)

Max Activating Token Index: 681

Text #8

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4312. Min Act: -0.0000

Data Index: 1041676 (The Pile)

Max Activating Token Index: 75

Text #9

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4463. Min Act: -0.0000

Data Index: 243924 (The Pile)

Max Activating Token Index: 203

Text #10

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1777704 (The Pile)

Max Activating Token Index: 997

Text #11

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1167214 (The Pile)

Max Activating Token Index: 601

Text #12

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4042. Min Act: -0.0000

Data Index: 54079 (The Pile)

Max Activating Token Index: 114

Text #13

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4282. Min Act: -0.0000

Data Index: 923972 (The Pile)

Max Activating Token Index: 54

Text #14

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1570180 (The Pile)

Max Activating Token Index: 899

Text #15

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4114. Min Act: -0.0000

Data Index: 286132 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1190979 (The Pile)

Max Activating Token Index: 640

Text #17

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4211. Min Act: -0.0000

Data Index: 1160023 (The Pile)

Max Activating Token Index: 730

Text #18

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4044. Min Act: -0.0000

Data Index: 914306 (The Pile)

Max Activating Token Index: 209

Text #19

Max Range: 0.5745. Min Range: -0.5745

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1638577 (The Pile)

Max Activating Token Index: 960