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

Dataset: The Pile

Neuron 5040 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.2536. Min Act: -0.0000

Data Index: 1595303 (The Pile)

Max Activating Token Index: 959

Text #1

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.0115. Min Act: -0.0000

Data Index: 1787845 (The Pile)

Max Activating Token Index: 545

Text #2

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.9393. Min Act: -0.0000

Data Index: 891035 (The Pile)

Max Activating Token Index: 872

Text #3

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.9582. Min Act: -0.0000

Data Index: 234018 (The Pile)

Max Activating Token Index: 749

Text #4

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.9647. Min Act: -0.0000

Data Index: 1122392 (The Pile)

Max Activating Token Index: 999

Text #5

Max Range: 3.2536. Min Range: -3.2536

Max Act: 3.1009. Min Act: -0.0000

Data Index: 508789 (The Pile)

Max Activating Token Index: 510

Text #6

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.9488. Min Act: -0.0000

Data Index: 1729332 (The Pile)

Max Activating Token Index: 623

Text #7

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.7740. Min Act: -0.0000

Data Index: 829521 (The Pile)

Max Activating Token Index: 991

Text #8

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.4246. Min Act: -0.0000

Data Index: 1959141 (The Pile)

Max Activating Token Index: 80

Text #9

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.7412. Min Act: -0.0000

Data Index: 387874 (The Pile)

Max Activating Token Index: 1002

Text #10

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.3396. Min Act: -0.0000

Data Index: 1960459 (The Pile)

Max Activating Token Index: 783

Text #11

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.6455. Min Act: -0.0000

Data Index: 620856 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.3810. Min Act: -0.0000

Data Index: 358330 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.4652. Min Act: -0.0000

Data Index: 850271 (The Pile)

Max Activating Token Index: 147

Text #14

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.3114. Min Act: -0.0000

Data Index: 880809 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.4070. Min Act: -0.0000

Data Index: 1080975 (The Pile)

Max Activating Token Index: 774

Text #16

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.5674. Min Act: -0.0000

Data Index: 1628052 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.4071. Min Act: -0.0000

Data Index: 1066702 (The Pile)

Max Activating Token Index: 792

Text #18

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.4044. Min Act: -0.0000

Data Index: 1231097 (The Pile)

Max Activating Token Index: 396

Text #19

Max Range: 3.2536. Min Range: -3.2536

Max Act: 2.5514. Min Act: -0.0000

Data Index: 76309 (The Pile)

Max Activating Token Index: 459