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

Dataset: The Pile

Neuron 3110 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: 0.7038. Min Range: -0.7038

Max Act: 0.6458. Min Act: -0.0000

Data Index: 1835883 (The Pile)

Max Activating Token Index: 660

Text #1

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1006837 (The Pile)

Max Activating Token Index: 582

Text #2

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6583. Min Act: -0.0000

Data Index: 1195361 (The Pile)

Max Activating Token Index: 284

Text #3

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1132237 (The Pile)

Max Activating Token Index: 276

Text #4

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6300. Min Act: -0.0000

Data Index: 670802 (The Pile)

Max Activating Token Index: 316

Text #5

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5989. Min Act: -0.0000

Data Index: 1964652 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6511. Min Act: 0.0000

Data Index: 1645310 (The Pile)

Max Activating Token Index: 561

Text #7

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1654805 (The Pile)

Max Activating Token Index: 587

Text #8

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1895215 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1461026 (The Pile)

Max Activating Token Index: 747

Text #10

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1614050 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5865. Min Act: 0.0000

Data Index: 499302 (The Pile)

Max Activating Token Index: 631

Text #12

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1096474 (The Pile)

Max Activating Token Index: 368

Text #13

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5679. Min Act: -0.0000

Data Index: 169051 (The Pile)

Max Activating Token Index: 1021

Text #14

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6048. Min Act: -0.0000

Data Index: 380934 (The Pile)

Max Activating Token Index: 218

Text #15

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6300. Min Act: -0.0000

Data Index: 613837 (The Pile)

Max Activating Token Index: 121

Text #16

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6213. Min Act: 0.0000

Data Index: 1909186 (The Pile)

Max Activating Token Index: 392

Text #17

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1055844 (The Pile)

Max Activating Token Index: 866

Text #18

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1349390 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.6288. Min Act: 0.0001

Data Index: 171032 (The Pile)

Max Activating Token Index: 766