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

Dataset: The Pile

Neuron 1186 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1718862 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5304. Min Act: -0.0000

Data Index: 421811 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5301. Min Act: 0.0000

Data Index: 999649 (The Pile)

Max Activating Token Index: 62

Text #3

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.5082. Min Act: -0.0000

Data Index: 938159 (The Pile)

Max Activating Token Index: 51

Text #4

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4971. Min Act: 0.0000

Data Index: 1585109 (The Pile)

Max Activating Token Index: 422

Text #5

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4446. Min Act: -0.0000

Data Index: 418754 (The Pile)

Max Activating Token Index: 806

Text #6

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4602. Min Act: -0.0000

Data Index: 691905 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1875259 (The Pile)

Max Activating Token Index: 498

Text #8

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.4065. Min Act: 0.0000

Data Index: 684049 (The Pile)

Max Activating Token Index: 552

Text #9

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3774. Min Act: 0.0000

Data Index: 1832262 (The Pile)

Max Activating Token Index: 9

Text #10

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3944. Min Act: -0.0000

Data Index: 963716 (The Pile)

Max Activating Token Index: 520

Text #11

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3657. Min Act: -0.0000

Data Index: 1041523 (The Pile)

Max Activating Token Index: 445

Text #12

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3597. Min Act: 0.0000

Data Index: 1378998 (The Pile)

Max Activating Token Index: 140

Text #13

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3792. Min Act: -0.0000

Data Index: 682179 (The Pile)

Max Activating Token Index: 654

Text #14

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1242354 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3402. Min Act: -0.0000

Data Index: 717542 (The Pile)

Max Activating Token Index: 235

Text #16

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3748. Min Act: -0.0000

Data Index: 125234 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1633503 (The Pile)

Max Activating Token Index: 86

Text #18

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3653. Min Act: -0.0000

Data Index: 1498736 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 0.5606. Min Range: -0.5606

Max Act: 0.3804. Min Act: -0.0000

Data Index: 900277 (The Pile)

Max Activating Token Index: 52