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

Dataset: The Pile

Neuron 2990 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: 1.9839. Min Range: -1.9839

Max Act: 1.9839. Min Act: -0.0000

Data Index: 1250579 (The Pile)

Max Activating Token Index: 997

Text #1

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.6350. Min Act: -0.0000

Data Index: 939280 (The Pile)

Max Activating Token Index: 473

Text #2

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.4715. Min Act: 0.0000

Data Index: 68890 (The Pile)

Max Activating Token Index: 486

Text #3

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.4435. Min Act: 0.0001

Data Index: 234804 (The Pile)

Max Activating Token Index: 458

Text #4

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.3837. Min Act: -0.0000

Data Index: 1431129 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.4465. Min Act: -0.0000

Data Index: 192675 (The Pile)

Max Activating Token Index: 851

Text #6

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.4313. Min Act: 0.0000

Data Index: 1523821 (The Pile)

Max Activating Token Index: 252

Text #7

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.3428. Min Act: 0.0000

Data Index: 1540240 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.4142. Min Act: -0.0000

Data Index: 538062 (The Pile)

Max Activating Token Index: 432

Text #9

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.4181. Min Act: -0.0000

Data Index: 695472 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.3542. Min Act: -0.0000

Data Index: 659082 (The Pile)

Max Activating Token Index: 561

Text #11

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.3711. Min Act: -0.0000

Data Index: 107234 (The Pile)

Max Activating Token Index: 198

Text #12

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.4389. Min Act: -0.0000

Data Index: 1868733 (The Pile)

Max Activating Token Index: 98

Text #13

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.3511. Min Act: -0.0000

Data Index: 1522329 (The Pile)

Max Activating Token Index: 140

Text #14

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.3463. Min Act: -0.0000

Data Index: 1573592 (The Pile)

Max Activating Token Index: 604

Text #15

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.3386. Min Act: -0.0000

Data Index: 1181960 (The Pile)

Max Activating Token Index: 491

Text #16

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.1311. Min Act: -0.0000

Data Index: 1268859 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.1793. Min Act: 0.0000

Data Index: 1967213 (The Pile)

Max Activating Token Index: 626

Text #18

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.3868. Min Act: -0.0000

Data Index: 173356 (The Pile)

Max Activating Token Index: 163

Text #19

Max Range: 1.9839. Min Range: -1.9839

Max Act: 1.4498. Min Act: -0.0000

Data Index: 544045 (The Pile)

Max Activating Token Index: 604