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

Dataset: The Pile

Neuron 4600 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: 1.3873. Min Range: -1.3873

Max Act: 1.3873. Min Act: -0.0000

Data Index: 310473 (The Pile)

Max Activating Token Index: 994

Text #1

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3142. Min Act: -0.0000

Data Index: 324568 (The Pile)

Max Activating Token Index: 568

Text #2

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3119. Min Act: -0.0000

Data Index: 286307 (The Pile)

Max Activating Token Index: 2

Text #3

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3119. Min Act: -0.0000

Data Index: 227091 (The Pile)

Max Activating Token Index: 2

Text #4

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2632. Min Act: -0.0000

Data Index: 1534179 (The Pile)

Max Activating Token Index: 781

Text #5

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2277. Min Act: -0.0000

Data Index: 134103 (The Pile)

Max Activating Token Index: 861

Text #6

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.3006. Min Act: -0.0000

Data Index: 385230 (The Pile)

Max Activating Token Index: 977

Text #7

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2965. Min Act: -0.0000

Data Index: 1401121 (The Pile)

Max Activating Token Index: 916

Text #8

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2973. Min Act: -0.0000

Data Index: 720166 (The Pile)

Max Activating Token Index: 723

Text #9

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2521. Min Act: -0.0000

Data Index: 544298 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2495. Min Act: -0.0000

Data Index: 1579044 (The Pile)

Max Activating Token Index: 574

Text #11

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2340. Min Act: -0.0000

Data Index: 622386 (The Pile)

Max Activating Token Index: 753

Text #12

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2231. Min Act: -0.0000

Data Index: 1057247 (The Pile)

Max Activating Token Index: 809

Text #13

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1701311 (The Pile)

Max Activating Token Index: 816

Text #14

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2158. Min Act: -0.0000

Data Index: 1647987 (The Pile)

Max Activating Token Index: 799

Text #15

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2188. Min Act: -0.0000

Data Index: 590426 (The Pile)

Max Activating Token Index: 304

Text #16

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2822. Min Act: -0.0000

Data Index: 1754938 (The Pile)

Max Activating Token Index: 890

Text #17

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1993. Min Act: -0.0000

Data Index: 873976 (The Pile)

Max Activating Token Index: 119

Text #18

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.2122. Min Act: -0.0000

Data Index: 1278895 (The Pile)

Max Activating Token Index: 910

Text #19

Max Range: 1.3873. Min Range: -1.3873

Max Act: 1.1943. Min Act: -0.0000

Data Index: 1747015 (The Pile)

Max Activating Token Index: 1005