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

Dataset: The Pile

Neuron 211 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1019. Min Range: -1.1019

Max Act: 1.1019. Min Act: -0.0000

Data Index: 264873 (The Pile)

Max Activating Token Index: 688

Text #1

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.9605. Min Act: -0.0000

Data Index: 67520 (The Pile)

Max Activating Token Index: 465

Text #2

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.9195. Min Act: -0.0000

Data Index: 333949 (The Pile)

Max Activating Token Index: 272

Text #3

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1305984 (The Pile)

Max Activating Token Index: 79

Text #4

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1517610 (The Pile)

Max Activating Token Index: 102

Text #5

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.9067. Min Act: -0.0000

Data Index: 238973 (The Pile)

Max Activating Token Index: 608

Text #6

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1868564 (The Pile)

Max Activating Token Index: 161

Text #7

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.8404. Min Act: -0.0000

Data Index: 1687086 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.7910. Min Act: -0.0000

Data Index: 219750 (The Pile)

Max Activating Token Index: 717

Text #9

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6772. Min Act: -0.0000

Data Index: 589271 (The Pile)

Max Activating Token Index: 414

Text #10

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.7333. Min Act: -0.0000

Data Index: 531064 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1629817 (The Pile)

Max Activating Token Index: 546

Text #12

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6613. Min Act: -0.0000

Data Index: 660475 (The Pile)

Max Activating Token Index: 760

Text #13

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.7928. Min Act: -0.0000

Data Index: 1798637 (The Pile)

Max Activating Token Index: 523

Text #14

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.7192. Min Act: -0.0000

Data Index: 1580650 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.7055. Min Act: -0.0000

Data Index: 1247444 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6221. Min Act: -0.0000

Data Index: 1176171 (The Pile)

Max Activating Token Index: 888

Text #17

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6753. Min Act: -0.0000

Data Index: 1595465 (The Pile)

Max Activating Token Index: 17

Text #18

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6081. Min Act: -0.0000

Data Index: 878102 (The Pile)

Max Activating Token Index: 1003

Text #19

Max Range: 1.1019. Min Range: -1.1019

Max Act: 0.6731. Min Act: -0.0000

Data Index: 191361 (The Pile)

Max Activating Token Index: 349