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

Dataset: The Pile

Neuron 3869 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: 0.6468. Min Range: -0.6468

Max Act: 0.6468. Min Act: -0.0000

Data Index: 301530 (The Pile)

Max Activating Token Index: 40

Text #1

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.6120. Min Act: -0.0000

Data Index: 1431775 (The Pile)

Max Activating Token Index: 181

Text #2

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5976. Min Act: -0.0000

Data Index: 920764 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5823. Min Act: -0.0000

Data Index: 606802 (The Pile)

Max Activating Token Index: 329

Text #4

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1505860 (The Pile)

Max Activating Token Index: 674

Text #5

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1339609 (The Pile)

Max Activating Token Index: 452

Text #6

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5363. Min Act: -0.0000

Data Index: 349373 (The Pile)

Max Activating Token Index: 80

Text #7

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5364. Min Act: -0.0000

Data Index: 332239 (The Pile)

Max Activating Token Index: 214

Text #8

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5102. Min Act: -0.0000

Data Index: 557843 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1651251 (The Pile)

Max Activating Token Index: 264

Text #10

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1883943 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5318. Min Act: -0.0000

Data Index: 1670715 (The Pile)

Max Activating Token Index: 764

Text #12

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4801. Min Act: -0.0000

Data Index: 1502738 (The Pile)

Max Activating Token Index: 904

Text #13

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5261. Min Act: -0.0000

Data Index: 1238898 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1148840 (The Pile)

Max Activating Token Index: 674

Text #15

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4787. Min Act: -0.0000

Data Index: 523028 (The Pile)

Max Activating Token Index: 435

Text #16

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4975. Min Act: -0.0000

Data Index: 1407520 (The Pile)

Max Activating Token Index: 268

Text #17

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4756. Min Act: -0.0000

Data Index: 892891 (The Pile)

Max Activating Token Index: 280

Text #18

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1328068 (The Pile)

Max Activating Token Index: 148

Text #19

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4796. Min Act: -0.0000

Data Index: 470030 (The Pile)

Max Activating Token Index: 331