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

Dataset: The Pile

Neuron 3538 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.8534. Min Act: -0.0000

Data Index: 1622655 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1565381 (The Pile)

Max Activating Token Index: 287

Text #2

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1582993 (The Pile)

Max Activating Token Index: 241

Text #3

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.7245. Min Act: -0.0000

Data Index: 1535723 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.7519. Min Act: -0.0000

Data Index: 958103 (The Pile)

Max Activating Token Index: 276

Text #5

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.7175. Min Act: -0.0000

Data Index: 951721 (The Pile)

Max Activating Token Index: 147

Text #6

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6875. Min Act: -0.0000

Data Index: 96039 (The Pile)

Max Activating Token Index: 631

Text #7

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1428133 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1519379 (The Pile)

Max Activating Token Index: 377

Text #9

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6385. Min Act: -0.0000

Data Index: 837860 (The Pile)

Max Activating Token Index: 94

Text #10

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1132395 (The Pile)

Max Activating Token Index: 774

Text #11

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1455830 (The Pile)

Max Activating Token Index: 585

Text #12

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6020. Min Act: -0.0000

Data Index: 887918 (The Pile)

Max Activating Token Index: 62

Text #13

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.5749. Min Act: -0.0000

Data Index: 340504 (The Pile)

Max Activating Token Index: 376

Text #14

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1262037 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1986519 (The Pile)

Max Activating Token Index: 523

Text #16

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.5931. Min Act: -0.0000

Data Index: 198856 (The Pile)

Max Activating Token Index: 53

Text #17

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1881642 (The Pile)

Max Activating Token Index: 686

Text #18

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1994613 (The Pile)

Max Activating Token Index: 387

Text #19

Max Range: 0.8534. Min Range: -0.8534

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1541696 (The Pile)

Max Activating Token Index: 995