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

Dataset: The Pile

Neuron 4795 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: 0.6062. Min Range: -0.6062

Max Act: 0.6062. Min Act: -0.0000

Data Index: 161542 (The Pile)

Max Activating Token Index: 251

Text #1

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5561. Min Act: -0.0000

Data Index: 902240 (The Pile)

Max Activating Token Index: 267

Text #2

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1618078 (The Pile)

Max Activating Token Index: 344

Text #3

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1270685 (The Pile)

Max Activating Token Index: 514

Text #4

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5278. Min Act: -0.0000

Data Index: 863638 (The Pile)

Max Activating Token Index: 341

Text #5

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5040. Min Act: -0.0000

Data Index: 51659 (The Pile)

Max Activating Token Index: 268

Text #6

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4706. Min Act: -0.0000

Data Index: 475832 (The Pile)

Max Activating Token Index: 223

Text #7

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4632. Min Act: -0.0000

Data Index: 388155 (The Pile)

Max Activating Token Index: 485

Text #8

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5424. Min Act: -0.0000

Data Index: 611232 (The Pile)

Max Activating Token Index: 268

Text #9

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.5271. Min Act: -0.0000

Data Index: 533545 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1937022 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1927091 (The Pile)

Max Activating Token Index: 167

Text #12

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4594. Min Act: -0.0000

Data Index: 165474 (The Pile)

Max Activating Token Index: 807

Text #13

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4390. Min Act: -0.0000

Data Index: 818746 (The Pile)

Max Activating Token Index: 359

Text #14

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1730722 (The Pile)

Max Activating Token Index: 494

Text #15

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4117. Min Act: -0.0000

Data Index: 938874 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4093. Min Act: -0.0000

Data Index: 997798 (The Pile)

Max Activating Token Index: 867

Text #17

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1593959 (The Pile)

Max Activating Token Index: 161

Text #18

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1967520 (The Pile)

Max Activating Token Index: 561

Text #19

Max Range: 0.6062. Min Range: -0.6062

Max Act: 0.4369. Min Act: -0.0000

Data Index: 74315 (The Pile)

Max Activating Token Index: 173