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

Dataset: The Pile

Neuron 238 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.9696. Min Act: -0.0000

Data Index: 1262941 (The Pile)

Max Activating Token Index: 365

Text #1

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.9379. Min Act: -0.0000

Data Index: 1851565 (The Pile)

Max Activating Token Index: 509

Text #2

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.9219. Min Act: -0.0000

Data Index: 670997 (The Pile)

Max Activating Token Index: 633

Text #3

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.9301. Min Act: -0.0000

Data Index: 1943174 (The Pile)

Max Activating Token Index: 285

Text #4

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.6978. Min Act: -0.0000

Data Index: 1200008 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.8712. Min Act: -0.0000

Data Index: 826995 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.8065. Min Act: -0.0000

Data Index: 125281 (The Pile)

Max Activating Token Index: 1002

Text #7

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.6863. Min Act: -0.0000

Data Index: 1276384 (The Pile)

Max Activating Token Index: 623

Text #8

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.7748. Min Act: -0.0000

Data Index: 1719120 (The Pile)

Max Activating Token Index: 522

Text #9

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.7178. Min Act: -0.0000

Data Index: 1861441 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.7047. Min Act: -0.0000

Data Index: 1190844 (The Pile)

Max Activating Token Index: 19

Text #11

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.5686. Min Act: -0.0000

Data Index: 1861711 (The Pile)

Max Activating Token Index: 79

Text #12

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.5763. Min Act: -0.0000

Data Index: 1452268 (The Pile)

Max Activating Token Index: 37

Text #13

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.7221. Min Act: -0.0000

Data Index: 1377316 (The Pile)

Max Activating Token Index: 925

Text #14

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.6452. Min Act: -0.0000

Data Index: 894638 (The Pile)

Max Activating Token Index: 399

Text #15

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.6366. Min Act: -0.0000

Data Index: 1596264 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.6375. Min Act: -0.0000

Data Index: 1795933 (The Pile)

Max Activating Token Index: 168

Text #17

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.5124. Min Act: -0.0000

Data Index: 1252632 (The Pile)

Max Activating Token Index: 59

Text #18

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.4889. Min Act: -0.0000

Data Index: 204537 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 1.9696. Min Range: -1.9696

Max Act: 1.4637. Min Act: -0.0000

Data Index: 762017 (The Pile)

Max Activating Token Index: 827