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

Dataset: The Pile

Neuron 2017 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2556. Min Range: -1.2556

Max Act: 1.2556. Min Act: -0.0000

Data Index: 1731424 (The Pile)

Max Activating Token Index: 44

Text #1

Max Range: 1.2556. Min Range: -1.2556

Max Act: 1.1439. Min Act: -0.0000

Data Index: 1865353 (The Pile)

Max Activating Token Index: 420

Text #2

Max Range: 1.2556. Min Range: -1.2556

Max Act: 1.0528. Min Act: -0.0000

Data Index: 166081 (The Pile)

Max Activating Token Index: 288

Text #3

Max Range: 1.2556. Min Range: -1.2556

Max Act: 1.0644. Min Act: -0.0000

Data Index: 108180 (The Pile)

Max Activating Token Index: 480

Text #4

Max Range: 1.2556. Min Range: -1.2556

Max Act: 0.9898. Min Act: -0.0000

Data Index: 1608838 (The Pile)

Max Activating Token Index: 88

Text #5

Max Range: 1.2556. Min Range: -1.2556

Max Act: 1.0345. Min Act: -0.0000

Data Index: 464488 (The Pile)

Max Activating Token Index: 424

Text #6

Max Range: 1.2556. Min Range: -1.2556

Max Act: 0.9602. Min Act: -0.0000

Data Index: 64543 (The Pile)

Max Activating Token Index: 169

Text #7

Max Range: 1.2556. Min Range: -1.2556

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1784842 (The Pile)

Max Activating Token Index: 791

Text #8

Max Range: 1.2556. Min Range: -1.2556

Max Act: 0.9700. Min Act: -0.0000

Data Index: 367699 (The Pile)

Max Activating Token Index: 354

Text #9

Max Range: 1.2556. Min Range: -1.2556

Max Act: 0.9911. Min Act: -0.0000

Data Index: 1612245 (The Pile)

Max Activating Token Index: 932

Text #10

Max Range: 1.2556. Min Range: -1.2556

Max Act: 1.0350. Min Act: -0.0000

Data Index: 555504 (The Pile)

Max Activating Token Index: 93

Text #11

Max Range: 1.2556. Min Range: -1.2556

Max Act: 0.8734. Min Act: -0.0000

Data Index: 1185062 (The Pile)

Max Activating Token Index: 117

Text #12

Max Range: 1.2556. Min Range: -1.2556

Max Act: 0.9098. Min Act: -0.0000

Data Index: 462139 (The Pile)

Max Activating Token Index: 470

Text #13

Max Range: 1.2556. Min Range: -1.2556

Max Act: 0.8663. Min Act: -0.0000

Data Index: 589990 (The Pile)

Max Activating Token Index: 905

Text #14

Max Range: 1.2556. Min Range: -1.2556

Max Act: 0.9111. Min Act: -0.0000

Data Index: 487624 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 1.2556. Min Range: -1.2556

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1471497 (The Pile)

Max Activating Token Index: 412

Text #16

Max Range: 1.2556. Min Range: -1.2556

Max Act: 0.9039. Min Act: -0.0000

Data Index: 952662 (The Pile)

Max Activating Token Index: 765

Text #17

Max Range: 1.2556. Min Range: -1.2556

Max Act: 0.8073. Min Act: -0.0000

Data Index: 430925 (The Pile)

Max Activating Token Index: 665

Text #18

Max Range: 1.2556. Min Range: -1.2556

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1716512 (The Pile)

Max Activating Token Index: 621

Text #19

Max Range: 1.2556. Min Range: -1.2556

Max Act: 0.8331. Min Act: -0.0000

Data Index: 790608 (The Pile)

Max Activating Token Index: 750