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

Dataset: The Pile

Neuron 4373 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: 1.1607. Min Range: -1.1607

Max Act: 1.1607. Min Act: -0.0000

Data Index: 485509 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.0628. Min Act: -0.0000

Data Index: 1013720 (The Pile)

Max Activating Token Index: 760

Text #2

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.1254. Min Act: -0.0000

Data Index: 321922 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9794. Min Act: -0.0000

Data Index: 641501 (The Pile)

Max Activating Token Index: 863

Text #4

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9936. Min Act: -0.0000

Data Index: 905446 (The Pile)

Max Activating Token Index: 1009

Text #5

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1767733 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.0085. Min Act: -0.0000

Data Index: 978843 (The Pile)

Max Activating Token Index: 601

Text #7

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8621. Min Act: -0.0000

Data Index: 998441 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1981298 (The Pile)

Max Activating Token Index: 752

Text #9

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.9676. Min Act: -0.0000

Data Index: 93265 (The Pile)

Max Activating Token Index: 139

Text #10

Max Range: 1.1607. Min Range: -1.1607

Max Act: 1.0618. Min Act: -0.0000

Data Index: 224546 (The Pile)

Max Activating Token Index: 928

Text #11

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8877. Min Act: -0.0000

Data Index: 1502616 (The Pile)

Max Activating Token Index: 721

Text #12

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8702. Min Act: -0.0000

Data Index: 1741264 (The Pile)

Max Activating Token Index: 132

Text #13

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.7874. Min Act: -0.0000

Data Index: 763505 (The Pile)

Max Activating Token Index: 253

Text #14

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8072. Min Act: -0.0000

Data Index: 167925 (The Pile)

Max Activating Token Index: 572

Text #15

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8191. Min Act: -0.0000

Data Index: 1676633 (The Pile)

Max Activating Token Index: 10

Text #16

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1558146 (The Pile)

Max Activating Token Index: 7

Text #17

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8163. Min Act: -0.0000

Data Index: 177339 (The Pile)

Max Activating Token Index: 760

Text #18

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.8065. Min Act: -0.0000

Data Index: 616319 (The Pile)

Max Activating Token Index: 771

Text #19

Max Range: 1.1607. Min Range: -1.1607

Max Act: 0.7631. Min Act: -0.0000

Data Index: 898909 (The Pile)

Max Activating Token Index: 876