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

Dataset: The Pile

Neuron 94 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.8373. Min Act: -0.0000

Data Index: 1252658 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.6671. Min Act: -0.0000

Data Index: 830115 (The Pile)

Max Activating Token Index: 869

Text #2

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.8623. Min Act: -0.0000

Data Index: 1193875 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.6677. Min Act: -0.0000

Data Index: 1815419 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.6701. Min Act: -0.0000

Data Index: 787175 (The Pile)

Max Activating Token Index: 94

Text #5

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.5788. Min Act: -0.0000

Data Index: 1600555 (The Pile)

Max Activating Token Index: 808

Text #6

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.4916. Min Act: -0.0000

Data Index: 1777216 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.5972. Min Act: -0.0000

Data Index: 822257 (The Pile)

Max Activating Token Index: 611

Text #8

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.5495. Min Act: -0.0000

Data Index: 1149068 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.7214. Min Act: -0.0000

Data Index: 1108640 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.6142. Min Act: -0.0000

Data Index: 428795 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.5622. Min Act: -0.0000

Data Index: 362162 (The Pile)

Max Activating Token Index: 151

Text #12

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.5911. Min Act: -0.0000

Data Index: 1472951 (The Pile)

Max Activating Token Index: 169

Text #13

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.5987. Min Act: -0.0000

Data Index: 884087 (The Pile)

Max Activating Token Index: 159

Text #14

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.5814. Min Act: -0.0000

Data Index: 1965183 (The Pile)

Max Activating Token Index: 149

Text #15

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.5116. Min Act: -0.0000

Data Index: 769345 (The Pile)

Max Activating Token Index: 813

Text #16

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.6046. Min Act: -0.0000

Data Index: 552064 (The Pile)

Max Activating Token Index: 819

Text #17

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.5586. Min Act: -0.0000

Data Index: 1451411 (The Pile)

Max Activating Token Index: 572

Text #18

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.4681. Min Act: -0.0000

Data Index: 1947757 (The Pile)

Max Activating Token Index: 288

Text #19

Max Range: 1.8623. Min Range: -1.8623

Max Act: 1.5378. Min Act: -0.0000

Data Index: 1901097 (The Pile)

Max Activating Token Index: 61