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

Dataset: The Pile

Neuron 243 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: 0.7002. Min Range: -0.7002

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1873836 (The Pile)

Max Activating Token Index: 936

Text #1

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1291803 (The Pile)

Max Activating Token Index: 875

Text #2

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.6871. Min Act: -0.0000

Data Index: 3425 (The Pile)

Max Activating Token Index: 1003

Text #3

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.6740. Min Act: -0.0000

Data Index: 1231755 (The Pile)

Max Activating Token Index: 1009

Text #4

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1244675 (The Pile)

Max Activating Token Index: 584

Text #5

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1256565 (The Pile)

Max Activating Token Index: 718

Text #6

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.6325. Min Act: -0.0000

Data Index: 83538 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1886840 (The Pile)

Max Activating Token Index: 947

Text #8

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.5682. Min Act: 0.0001

Data Index: 1504444 (The Pile)

Max Activating Token Index: 337

Text #9

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.5128. Min Act: -0.0000

Data Index: 864744 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1524731 (The Pile)

Max Activating Token Index: 359

Text #11

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1064068 (The Pile)

Max Activating Token Index: 911

Text #12

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1046439 (The Pile)

Max Activating Token Index: 686

Text #13

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4793. Min Act: -0.0000

Data Index: 343963 (The Pile)

Max Activating Token Index: 969

Text #14

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4706. Min Act: -0.0000

Data Index: 630609 (The Pile)

Max Activating Token Index: 660

Text #15

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.5158. Min Act: -0.0001

Data Index: 1840472 (The Pile)

Max Activating Token Index: 860

Text #16

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4794. Min Act: -0.0000

Data Index: 43224 (The Pile)

Max Activating Token Index: 487

Text #17

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4656. Min Act: -0.0000

Data Index: 420599 (The Pile)

Max Activating Token Index: 785

Text #18

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4571. Min Act: -0.0000

Data Index: 122384 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 0.7002. Min Range: -0.7002

Max Act: 0.4377. Min Act: -0.0000

Data Index: 618210 (The Pile)

Max Activating Token Index: 852