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

Dataset: The Pile

Neuron 805 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: 1.6811. Min Range: -1.6811

Max Act: 1.6811. Min Act: -0.0000

Data Index: 1463192 (The Pile)

Max Activating Token Index: 55

Text #1

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.3364. Min Act: -0.0000

Data Index: 393841 (The Pile)

Max Activating Token Index: 53

Text #2

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.3079. Min Act: -0.0000

Data Index: 1814578 (The Pile)

Max Activating Token Index: 106

Text #3

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.3317. Min Act: -0.0000

Data Index: 296386 (The Pile)

Max Activating Token Index: 54

Text #4

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1046. Min Act: -0.0000

Data Index: 1503029 (The Pile)

Max Activating Token Index: 693

Text #5

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2954. Min Act: -0.0000

Data Index: 1561119 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.3195. Min Act: -0.0000

Data Index: 1132763 (The Pile)

Max Activating Token Index: 168

Text #7

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2418. Min Act: -0.0000

Data Index: 331156 (The Pile)

Max Activating Token Index: 649

Text #8

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1910. Min Act: -0.0000

Data Index: 1675517 (The Pile)

Max Activating Token Index: 933

Text #9

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1898. Min Act: -0.0000

Data Index: 1086806 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1848. Min Act: -0.0000

Data Index: 7860 (The Pile)

Max Activating Token Index: 222

Text #11

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.3495. Min Act: -0.0000

Data Index: 299274 (The Pile)

Max Activating Token Index: 757

Text #12

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2823. Min Act: -0.0000

Data Index: 1375269 (The Pile)

Max Activating Token Index: 37

Text #13

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1492. Min Act: -0.0000

Data Index: 1790912 (The Pile)

Max Activating Token Index: 506

Text #14

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1907. Min Act: -0.0000

Data Index: 981476 (The Pile)

Max Activating Token Index: 255

Text #15

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1276953 (The Pile)

Max Activating Token Index: 934

Text #16

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.4348. Min Act: -0.0000

Data Index: 927929 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1209. Min Act: -0.0000

Data Index: 153590 (The Pile)

Max Activating Token Index: 792

Text #18

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.1817. Min Act: -0.0000

Data Index: 1263001 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 1.6811. Min Range: -1.6811

Max Act: 1.2045. Min Act: -0.0000

Data Index: 1706384 (The Pile)

Max Activating Token Index: 745