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

Dataset: The Pile

Neuron 4915 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: 1.4345. Min Range: -1.4345

Max Act: 1.4345. Min Act: -0.0000

Data Index: 1192937 (The Pile)

Max Activating Token Index: 236

Text #1

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2611. Min Act: -0.0000

Data Index: 560991 (The Pile)

Max Activating Token Index: 402

Text #2

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2711. Min Act: -0.0000

Data Index: 195981 (The Pile)

Max Activating Token Index: 392

Text #3

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2109. Min Act: -0.0000

Data Index: 940757 (The Pile)

Max Activating Token Index: 497

Text #4

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2620. Min Act: -0.0000

Data Index: 1946966 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.2246. Min Act: -0.0000

Data Index: 1074607 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.1287. Min Act: -0.0000

Data Index: 428792 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.1401. Min Act: -0.0000

Data Index: 1835253 (The Pile)

Max Activating Token Index: 430

Text #8

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.1360. Min Act: -0.0000

Data Index: 1195469 (The Pile)

Max Activating Token Index: 396

Text #9

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.1364. Min Act: -0.0000

Data Index: 800320 (The Pile)

Max Activating Token Index: 493

Text #10

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.1031. Min Act: -0.0000

Data Index: 68805 (The Pile)

Max Activating Token Index: 563

Text #11

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.0929. Min Act: -0.0000

Data Index: 148404 (The Pile)

Max Activating Token Index: 64

Text #12

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.0666. Min Act: -0.0000

Data Index: 1948662 (The Pile)

Max Activating Token Index: 649

Text #13

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.1304. Min Act: -0.0000

Data Index: 903800 (The Pile)

Max Activating Token Index: 113

Text #14

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.0472. Min Act: -0.0000

Data Index: 1910871 (The Pile)

Max Activating Token Index: 15

Text #15

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.0193. Min Act: -0.0000

Data Index: 316001 (The Pile)

Max Activating Token Index: 852

Text #16

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.0730. Min Act: -0.0000

Data Index: 1648679 (The Pile)

Max Activating Token Index: 411

Text #17

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.0373. Min Act: -0.0000

Data Index: 1365978 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.0637. Min Act: -0.0000

Data Index: 239309 (The Pile)

Max Activating Token Index: 885

Text #19

Max Range: 1.4345. Min Range: -1.4345

Max Act: 1.0586. Min Act: -0.0001

Data Index: 567708 (The Pile)

Max Activating Token Index: 892