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

Dataset: The Pile

Neuron 1204 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.4561. Min Act: -0.0000

Data Index: 1108267 (The Pile)

Max Activating Token Index: 36

Text #1

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.2486. Min Act: -0.0000

Data Index: 1681242 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.6648. Min Act: -0.0000

Data Index: 34605 (The Pile)

Max Activating Token Index: 912

Text #3

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.2187. Min Act: -0.0000

Data Index: 1536376 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1773944 (The Pile)

Max Activating Token Index: 964

Text #5

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.2043. Min Act: -0.0000

Data Index: 1124288 (The Pile)

Max Activating Token Index: 640

Text #6

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.1242. Min Act: -0.0000

Data Index: 468359 (The Pile)

Max Activating Token Index: 492

Text #7

Max Range: 1.6648. Min Range: -1.6648

Max Act: 1.1322. Min Act: -0.0000

Data Index: 1426336 (The Pile)

Max Activating Token Index: 911

Text #8

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1050964 (The Pile)

Max Activating Token Index: 871

Text #9

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1006022 (The Pile)

Max Activating Token Index: 296

Text #10

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.5734. Min Act: -0.0000

Data Index: 335345 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.5364. Min Act: -0.0000

Data Index: 3662 (The Pile)

Max Activating Token Index: 595

Text #12

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.5488. Min Act: -0.0000

Data Index: 178777 (The Pile)

Max Activating Token Index: 717

Text #13

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.5746. Min Act: -0.0000

Data Index: 448996 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.5959. Min Act: -0.0000

Data Index: 1319544 (The Pile)

Max Activating Token Index: 442

Text #15

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.6022. Min Act: -0.0000

Data Index: 796385 (The Pile)

Max Activating Token Index: 749

Text #16

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.4533. Min Act: -0.0000

Data Index: 869881 (The Pile)

Max Activating Token Index: 881

Text #17

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.5136. Min Act: -0.0000

Data Index: 388141 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1529933 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 1.6648. Min Range: -1.6648

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1074001 (The Pile)

Max Activating Token Index: 978