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

Dataset: The Pile

Neuron 1014 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: 0.9100. Min Range: -0.9100

Max Act: 0.8573. Min Act: -0.0000

Data Index: 157382 (The Pile)

Max Activating Token Index: 555

Text #1

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.9100. Min Act: -0.0000

Data Index: 906126 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1285145 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8487. Min Act: -0.0000

Data Index: 686114 (The Pile)

Max Activating Token Index: 845

Text #4

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8014. Min Act: -0.0000

Data Index: 72134 (The Pile)

Max Activating Token Index: 125

Text #5

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8029. Min Act: -0.0000

Data Index: 971336 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8212. Min Act: -0.0000

Data Index: 1213835 (The Pile)

Max Activating Token Index: 923

Text #7

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8216. Min Act: -0.0000

Data Index: 997146 (The Pile)

Max Activating Token Index: 210

Text #8

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8252. Min Act: -0.0000

Data Index: 557322 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1923220 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1410910 (The Pile)

Max Activating Token Index: 838

Text #11

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7780. Min Act: -0.0000

Data Index: 854205 (The Pile)

Max Activating Token Index: 437

Text #12

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1347673 (The Pile)

Max Activating Token Index: 710

Text #13

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7942. Min Act: -0.0000

Data Index: 712621 (The Pile)

Max Activating Token Index: 521

Text #14

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7586. Min Act: -0.0000

Data Index: 1049872 (The Pile)

Max Activating Token Index: 341

Text #15

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7451. Min Act: -0.0000

Data Index: 1783026 (The Pile)

Max Activating Token Index: 576

Text #16

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7439. Min Act: -0.0000

Data Index: 1756657 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1248251 (The Pile)

Max Activating Token Index: 117

Text #18

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7576. Min Act: -0.0000

Data Index: 324421 (The Pile)

Max Activating Token Index: 420

Text #19

Max Range: 0.9100. Min Range: -0.9100

Max Act: 0.7637. Min Act: -0.0000

Data Index: 870212 (The Pile)

Max Activating Token Index: 826