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

Dataset: The Pile

Neuron 3404 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: 1.7512. Min Range: -1.7512

Max Act: 1.7150. Min Act: -0.0000

Data Index: 772727 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.7116. Min Act: -0.0000

Data Index: 1786320 (The Pile)

Max Activating Token Index: 128

Text #2

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.6598. Min Act: -0.0000

Data Index: 1487888 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.6870. Min Act: -0.0000

Data Index: 356725 (The Pile)

Max Activating Token Index: 209

Text #4

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.7512. Min Act: -0.0000

Data Index: 687050 (The Pile)

Max Activating Token Index: 666

Text #5

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.5189. Min Act: -0.0000

Data Index: 531604 (The Pile)

Max Activating Token Index: 823

Text #6

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.6001. Min Act: -0.0000

Data Index: 1641795 (The Pile)

Max Activating Token Index: 511

Text #7

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.6438. Min Act: -0.0000

Data Index: 608334 (The Pile)

Max Activating Token Index: 494

Text #8

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.7095. Min Act: -0.0000

Data Index: 821216 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.5072. Min Act: -0.0000

Data Index: 493283 (The Pile)

Max Activating Token Index: 826

Text #10

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.5248. Min Act: -0.0000

Data Index: 898665 (The Pile)

Max Activating Token Index: 334

Text #11

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.4794. Min Act: -0.0000

Data Index: 999207 (The Pile)

Max Activating Token Index: 180

Text #12

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.6420. Min Act: -0.0000

Data Index: 1770842 (The Pile)

Max Activating Token Index: 40

Text #13

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.3396. Min Act: -0.0000

Data Index: 945122 (The Pile)

Max Activating Token Index: 488

Text #14

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.4653. Min Act: -0.0000

Data Index: 1840795 (The Pile)

Max Activating Token Index: 53

Text #15

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.4610. Min Act: -0.0000

Data Index: 1265808 (The Pile)

Max Activating Token Index: 487

Text #16

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.5394. Min Act: -0.0000

Data Index: 1859889 (The Pile)

Max Activating Token Index: 144

Text #17

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.5455. Min Act: -0.0000

Data Index: 353414 (The Pile)

Max Activating Token Index: 433

Text #18

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.5534. Min Act: -0.0000

Data Index: 898956 (The Pile)

Max Activating Token Index: 473

Text #19

Max Range: 1.7512. Min Range: -1.7512

Max Act: 1.4578. Min Act: -0.0000

Data Index: 127170 (The Pile)

Max Activating Token Index: 247