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

Dataset: The Pile

Neuron 4966 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: 0.1890. Min Range: -0.1890

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1688002 (The Pile)

Max Activating Token Index: 263

Text #1

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1824. Min Act: -0.0000

Data Index: 77359 (The Pile)

Max Activating Token Index: 385

Text #2

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1827. Min Act: -0.0000

Data Index: 935521 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1617. Min Act: -0.0000

Data Index: 876147 (The Pile)

Max Activating Token Index: 819

Text #4

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1618. Min Act: -0.0000

Data Index: 1550073 (The Pile)

Max Activating Token Index: 1008

Text #5

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1090936 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1376. Min Act: -0.0000

Data Index: 16021 (The Pile)

Max Activating Token Index: 590

Text #7

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1320734 (The Pile)

Max Activating Token Index: 571

Text #8

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1333. Min Act: -0.0000

Data Index: 633704 (The Pile)

Max Activating Token Index: 1013

Text #9

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1438. Min Act: -0.0000

Data Index: 498068 (The Pile)

Max Activating Token Index: 585

Text #10

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1311. Min Act: -0.0000

Data Index: 325000 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1303. Min Act: -0.0000

Data Index: 594877 (The Pile)

Max Activating Token Index: 587

Text #12

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1254. Min Act: -0.0000

Data Index: 142696 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1253. Min Act: -0.0000

Data Index: 829869 (The Pile)

Max Activating Token Index: 1008

Text #14

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1295. Min Act: -0.0000

Data Index: 180905 (The Pile)

Max Activating Token Index: 473

Text #15

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1335. Min Act: -0.0000

Data Index: 1930825 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1338. Min Act: -0.0000

Data Index: 73705 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1290. Min Act: -0.0000

Data Index: 994169 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1100070 (The Pile)

Max Activating Token Index: 229

Text #19

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1264. Min Act: -0.0000

Data Index: 438633 (The Pile)

Max Activating Token Index: 546