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

Dataset: The Pile

Neuron 3532 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: 0.6100. Min Range: -0.6100

Max Act: 0.6100. Min Act: -0.0000

Data Index: 1194169 (The Pile)

Max Activating Token Index: 550

Text #1

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.4381. Min Act: -0.0000

Data Index: 119495 (The Pile)

Max Activating Token Index: 806

Text #2

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3569. Min Act: -0.0000

Data Index: 822444 (The Pile)

Max Activating Token Index: 446

Text #3

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3679. Min Act: -0.0000

Data Index: 1644812 (The Pile)

Max Activating Token Index: 303

Text #4

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.2955. Min Act: -0.0000

Data Index: 581013 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.2980. Min Act: -0.0000

Data Index: 521189 (The Pile)

Max Activating Token Index: 172

Text #6

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.2890. Min Act: -0.0000

Data Index: 649112 (The Pile)

Max Activating Token Index: 934

Text #7

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3064. Min Act: -0.0000

Data Index: 332950 (The Pile)

Max Activating Token Index: 379

Text #8

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1746878 (The Pile)

Max Activating Token Index: 502

Text #9

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3002. Min Act: -0.0000

Data Index: 1815845 (The Pile)

Max Activating Token Index: 595

Text #10

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.3270. Min Act: -0.0000

Data Index: 1883429 (The Pile)

Max Activating Token Index: 517

Text #11

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.2889. Min Act: -0.0000

Data Index: 726462 (The Pile)

Max Activating Token Index: 781

Text #12

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1284996 (The Pile)

Max Activating Token Index: 61

Text #13

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.2749. Min Act: -0.0000

Data Index: 546231 (The Pile)

Max Activating Token Index: 271

Text #14

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1601322 (The Pile)

Max Activating Token Index: 480

Text #15

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.2684. Min Act: -0.0000

Data Index: 739784 (The Pile)

Max Activating Token Index: 648

Text #16

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1639222 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.2935. Min Act: -0.0000

Data Index: 74535 (The Pile)

Max Activating Token Index: 747

Text #18

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.2552. Min Act: -0.0000

Data Index: 993441 (The Pile)

Max Activating Token Index: 274

Text #19

Max Range: 0.6100. Min Range: -0.6100

Max Act: 0.2693. Min Act: -0.0000

Data Index: 8496 (The Pile)

Max Activating Token Index: 411