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

Dataset: The Pile

Neuron 1362 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0648. Min Act: -0.0000

Data Index: 1252760 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0433. Min Act: -0.0000

Data Index: 580943 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0276. Min Act: -0.0000

Data Index: 1156095 (The Pile)

Max Activating Token Index: 741

Text #3

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0034. Min Act: -0.0001

Data Index: 25436 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0249. Min Act: -0.0000

Data Index: 1005027 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0048. Min Act: -0.0000

Data Index: 169716 (The Pile)

Max Activating Token Index: 1007

Text #6

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0151. Min Act: -0.0000

Data Index: 362906 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1999413 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0083. Min Act: -0.0000

Data Index: 1571103 (The Pile)

Max Activating Token Index: 1018

Text #9

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9845. Min Act: -0.0000

Data Index: 901572 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9794. Min Act: -0.0000

Data Index: 503222 (The Pile)

Max Activating Token Index: 1007

Text #11

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1228023 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9420. Min Act: -0.0000

Data Index: 356559 (The Pile)

Max Activating Token Index: 1018

Text #13

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9218. Min Act: -0.0000

Data Index: 1723597 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9698. Min Act: -0.0000

Data Index: 1635116 (The Pile)

Max Activating Token Index: 836

Text #15

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9755. Min Act: -0.0000

Data Index: 1000840 (The Pile)

Max Activating Token Index: 1012

Text #16

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0409. Min Act: -0.0000

Data Index: 380220 (The Pile)

Max Activating Token Index: 265

Text #17

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9432. Min Act: -0.0000

Data Index: 390986 (The Pile)

Max Activating Token Index: 443

Text #18

Max Range: 1.0648. Min Range: -1.0648

Max Act: 1.0045. Min Act: -0.0000

Data Index: 243635 (The Pile)

Max Activating Token Index: 1010

Text #19

Max Range: 1.0648. Min Range: -1.0648

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1028634 (The Pile)

Max Activating Token Index: 1012