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

Dataset: The Pile

Neuron 2023 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: 5.3539. Min Range: -5.3539

Max Act: 5.3539. Min Act: -0.0000

Data Index: 110115 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 5.3539. Min Range: -5.3539

Max Act: 4.7559. Min Act: -0.0000

Data Index: 97375 (The Pile)

Max Activating Token Index: 622

Text #2

Max Range: 5.3539. Min Range: -5.3539

Max Act: 4.4987. Min Act: -0.0000

Data Index: 965892 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 5.3539. Min Range: -5.3539

Max Act: 4.5647. Min Act: -0.0000

Data Index: 1778380 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 5.3539. Min Range: -5.3539

Max Act: 4.6975. Min Act: -0.0000

Data Index: 1324795 (The Pile)

Max Activating Token Index: 750

Text #5

Max Range: 5.3539. Min Range: -5.3539

Max Act: 4.6811. Min Act: -0.0000

Data Index: 1070727 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 5.3539. Min Range: -5.3539

Max Act: 4.7385. Min Act: -0.0000

Data Index: 1900451 (The Pile)

Max Activating Token Index: 1014

Text #7

Max Range: 5.3539. Min Range: -5.3539

Max Act: 4.3010. Min Act: -0.0000

Data Index: 1047814 (The Pile)

Max Activating Token Index: 1001

Text #8

Max Range: 5.3539. Min Range: -5.3539

Max Act: 4.1237. Min Act: -0.0000

Data Index: 1747321 (The Pile)

Max Activating Token Index: 783

Text #9

Max Range: 5.3539. Min Range: -5.3539

Max Act: 4.1185. Min Act: -0.0000

Data Index: 1242089 (The Pile)

Max Activating Token Index: 276

Text #10

Max Range: 5.3539. Min Range: -5.3539

Max Act: 4.1411. Min Act: -0.0000

Data Index: 1567972 (The Pile)

Max Activating Token Index: 299

Text #11

Max Range: 5.3539. Min Range: -5.3539

Max Act: 4.0690. Min Act: -0.0000

Data Index: 354863 (The Pile)

Max Activating Token Index: 306

Text #12

Max Range: 5.3539. Min Range: -5.3539

Max Act: 3.9633. Min Act: -0.0000

Data Index: 469630 (The Pile)

Max Activating Token Index: 830

Text #13

Max Range: 5.3539. Min Range: -5.3539

Max Act: 3.9771. Min Act: -0.0000

Data Index: 129972 (The Pile)

Max Activating Token Index: 976

Text #14

Max Range: 5.3539. Min Range: -5.3539

Max Act: 3.9770. Min Act: -0.0000

Data Index: 1919899 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 5.3539. Min Range: -5.3539

Max Act: 3.7880. Min Act: -0.0000

Data Index: 1444671 (The Pile)

Max Activating Token Index: 60

Text #16

Max Range: 5.3539. Min Range: -5.3539

Max Act: 3.5773. Min Act: -0.0000

Data Index: 958933 (The Pile)

Max Activating Token Index: 891

Text #17

Max Range: 5.3539. Min Range: -5.3539

Max Act: 4.0186. Min Act: -0.0000

Data Index: 1019494 (The Pile)

Max Activating Token Index: 127

Text #18

Max Range: 5.3539. Min Range: -5.3539

Max Act: 3.8025. Min Act: -0.0000

Data Index: 1339748 (The Pile)

Max Activating Token Index: 65

Text #19

Max Range: 5.3539. Min Range: -5.3539

Max Act: 3.4252. Min Act: -0.0000

Data Index: 1761135 (The Pile)

Max Activating Token Index: 648