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

Dataset: The Pile

Neuron 4403 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: 0.4677. Min Range: -0.4677

Max Act: 0.4677. Min Act: -0.0000

Data Index: 737567 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1248058 (The Pile)

Max Activating Token Index: 989

Text #2

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1718523 (The Pile)

Max Activating Token Index: 120

Text #3

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1426695 (The Pile)

Max Activating Token Index: 699

Text #4

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3933. Min Act: -0.0000

Data Index: 542734 (The Pile)

Max Activating Token Index: 219

Text #5

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.4025. Min Act: -0.0000

Data Index: 583965 (The Pile)

Max Activating Token Index: 1002

Text #6

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3998. Min Act: 0.0000

Data Index: 619281 (The Pile)

Max Activating Token Index: 1010

Text #7

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1230612 (The Pile)

Max Activating Token Index: 788

Text #8

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3527. Min Act: -0.0000

Data Index: 20198 (The Pile)

Max Activating Token Index: 944

Text #9

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3680. Min Act: -0.0000

Data Index: 474701 (The Pile)

Max Activating Token Index: 850

Text #10

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3629. Min Act: -0.0000

Data Index: 1956945 (The Pile)

Max Activating Token Index: 89

Text #11

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3610. Min Act: 0.0000

Data Index: 1295800 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1800373 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3595. Min Act: -0.0000

Data Index: 377983 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3351. Min Act: -0.0000

Data Index: 1445128 (The Pile)

Max Activating Token Index: 631

Text #15

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1317336 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3538. Min Act: -0.0000

Data Index: 225207 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3629. Min Act: -0.0000

Data Index: 685356 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3369. Min Act: -0.0000

Data Index: 218276 (The Pile)

Max Activating Token Index: 515

Text #19

Max Range: 0.4677. Min Range: -0.4677

Max Act: 0.3478. Min Act: -0.0000

Data Index: 336709 (The Pile)

Max Activating Token Index: 285