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

Dataset: The Pile

Neuron 201 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1683. Min Range: -1.1683

Max Act: 1.1661. Min Act: -0.0000

Data Index: 293268 (The Pile)

Max Activating Token Index: 531

Text #1

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9984. Min Act: -0.0000

Data Index: 1180340 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 1.1683. Min Range: -1.1683

Max Act: 1.1683. Min Act: -0.0000

Data Index: 777980 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 1.1683. Min Range: -1.1683

Max Act: 1.0178. Min Act: -0.0000

Data Index: 1725772 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9971. Min Act: -0.0000

Data Index: 71003 (The Pile)

Max Activating Token Index: 491

Text #5

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9501. Min Act: -0.0000

Data Index: 1448499 (The Pile)

Max Activating Token Index: 666

Text #6

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1155974 (The Pile)

Max Activating Token Index: 735

Text #7

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9081. Min Act: -0.0000

Data Index: 32999 (The Pile)

Max Activating Token Index: 606

Text #8

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9055. Min Act: -0.0000

Data Index: 679588 (The Pile)

Max Activating Token Index: 240

Text #9

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9076. Min Act: -0.0000

Data Index: 91201 (The Pile)

Max Activating Token Index: 668

Text #10

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9040. Min Act: -0.0000

Data Index: 142145 (The Pile)

Max Activating Token Index: 549

Text #11

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.9004. Min Act: -0.0000

Data Index: 908409 (The Pile)

Max Activating Token Index: 304

Text #12

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8807. Min Act: -0.0000

Data Index: 958603 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1723974 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8596. Min Act: -0.0000

Data Index: 1039120 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8610. Min Act: -0.0000

Data Index: 238897 (The Pile)

Max Activating Token Index: 965

Text #16

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8310. Min Act: -0.0000

Data Index: 569937 (The Pile)

Max Activating Token Index: 622

Text #17

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.7585. Min Act: -0.0000

Data Index: 698291 (The Pile)

Max Activating Token Index: 46

Text #18

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8185. Min Act: -0.0000

Data Index: 1706048 (The Pile)

Max Activating Token Index: 909

Text #19

Max Range: 1.1683. Min Range: -1.1683

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1583600 (The Pile)

Max Activating Token Index: 339