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

Dataset: The Pile

Neuron 1407 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.6039. Min Act: 0.0000

Data Index: 526959 (The Pile)

Max Activating Token Index: 28

Text #1

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.4923. Min Act: -0.0000

Data Index: 764868 (The Pile)

Max Activating Token Index: 285

Text #2

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.4850. Min Act: -0.0000

Data Index: 247165 (The Pile)

Max Activating Token Index: 840

Text #3

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.4064. Min Act: -0.0000

Data Index: 792740 (The Pile)

Max Activating Token Index: 341

Text #4

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.3101. Min Act: -0.0000

Data Index: 1749501 (The Pile)

Max Activating Token Index: 866

Text #5

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.3147. Min Act: -0.0000

Data Index: 955893 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.1217. Min Act: -0.0000

Data Index: 1310560 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.1188. Min Act: -0.0000

Data Index: 851749 (The Pile)

Max Activating Token Index: 627

Text #8

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.2515. Min Act: -0.0000

Data Index: 1541740 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1798998 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.3083. Min Act: -0.0000

Data Index: 786648 (The Pile)

Max Activating Token Index: 740

Text #11

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.1634. Min Act: -0.0000

Data Index: 608874 (The Pile)

Max Activating Token Index: 362

Text #12

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.2342. Min Act: -0.0000

Data Index: 489573 (The Pile)

Max Activating Token Index: 728

Text #13

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.2044. Min Act: -0.0000

Data Index: 1748536 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.1969. Min Act: -0.0000

Data Index: 1719012 (The Pile)

Max Activating Token Index: 414

Text #15

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.2523. Min Act: -0.0000

Data Index: 1009018 (The Pile)

Max Activating Token Index: 986

Text #16

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.2007. Min Act: -0.0000

Data Index: 1225231 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.1843. Min Act: -0.0000

Data Index: 1164827 (The Pile)

Max Activating Token Index: 185

Text #18

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.1755. Min Act: -0.0000

Data Index: 1794132 (The Pile)

Max Activating Token Index: 235

Text #19

Max Range: 1.6039. Min Range: -1.6039

Max Act: 1.1723. Min Act: -0.0000

Data Index: 238886 (The Pile)

Max Activating Token Index: 489