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

Dataset: The Pile

Neuron 757 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.6199. Min Act: -0.0000

Data Index: 23390 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.7008. Min Act: -0.0000

Data Index: 791357 (The Pile)

Max Activating Token Index: 360

Text #2

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.5499. Min Act: -0.0000

Data Index: 1300342 (The Pile)

Max Activating Token Index: 182

Text #3

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.5890. Min Act: -0.0000

Data Index: 1025608 (The Pile)

Max Activating Token Index: 412

Text #4

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.6478. Min Act: -0.0000

Data Index: 218987 (The Pile)

Max Activating Token Index: 140

Text #5

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.6342. Min Act: -0.0000

Data Index: 1825301 (The Pile)

Max Activating Token Index: 223

Text #6

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.5802. Min Act: -0.0000

Data Index: 1866204 (The Pile)

Max Activating Token Index: 273

Text #7

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.5631. Min Act: -0.0000

Data Index: 1440263 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.6133. Min Act: -0.0000

Data Index: 304506 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.5590. Min Act: -0.0000

Data Index: 1758324 (The Pile)

Max Activating Token Index: 514

Text #10

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.5793. Min Act: -0.0000

Data Index: 36779 (The Pile)

Max Activating Token Index: 697

Text #11

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.6053. Min Act: -0.0000

Data Index: 593354 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.3878. Min Act: -0.0000

Data Index: 1286583 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.4234. Min Act: -0.0000

Data Index: 257838 (The Pile)

Max Activating Token Index: 458

Text #14

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.5728. Min Act: -0.0000

Data Index: 478131 (The Pile)

Max Activating Token Index: 972

Text #15

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.5546. Min Act: -0.0000

Data Index: 557383 (The Pile)

Max Activating Token Index: 403

Text #16

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.6560. Min Act: -0.0000

Data Index: 1128310 (The Pile)

Max Activating Token Index: 71

Text #17

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.2572. Min Act: -0.0000

Data Index: 985103 (The Pile)

Max Activating Token Index: 916

Text #18

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.4181. Min Act: -0.0000

Data Index: 861522 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 1.7008. Min Range: -1.7008

Max Act: 1.4459. Min Act: -0.0000

Data Index: 155175 (The Pile)

Max Activating Token Index: 225