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

Dataset: The Pile

Neuron 3158 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4928. Min Range: -1.4928

Max Act: 1.4928. Min Act: -0.0000

Data Index: 1510000 (The Pile)

Max Activating Token Index: 35

Text #1

Max Range: 1.4928. Min Range: -1.4928

Max Act: 1.3274. Min Act: -0.0000

Data Index: 260422 (The Pile)

Max Activating Token Index: 735

Text #2

Max Range: 1.4928. Min Range: -1.4928

Max Act: 1.0994. Min Act: -0.0000

Data Index: 1931630 (The Pile)

Max Activating Token Index: 353

Text #3

Max Range: 1.4928. Min Range: -1.4928

Max Act: 1.0517. Min Act: -0.0000

Data Index: 518420 (The Pile)

Max Activating Token Index: 506

Text #4

Max Range: 1.4928. Min Range: -1.4928

Max Act: 1.0591. Min Act: -0.0000

Data Index: 614407 (The Pile)

Max Activating Token Index: 363

Text #5

Max Range: 1.4928. Min Range: -1.4928

Max Act: 1.1048. Min Act: -0.0000

Data Index: 958486 (The Pile)

Max Activating Token Index: 529

Text #6

Max Range: 1.4928. Min Range: -1.4928

Max Act: 1.0542. Min Act: -0.0000

Data Index: 1123501 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 1.4928. Min Range: -1.4928

Max Act: 1.0743. Min Act: -0.0000

Data Index: 750822 (The Pile)

Max Activating Token Index: 236

Text #8

Max Range: 1.4928. Min Range: -1.4928

Max Act: 0.9415. Min Act: -0.0000

Data Index: 1973884 (The Pile)

Max Activating Token Index: 852

Text #9

Max Range: 1.4928. Min Range: -1.4928

Max Act: 1.0000. Min Act: -0.0000

Data Index: 1022947 (The Pile)

Max Activating Token Index: 389

Text #10

Max Range: 1.4928. Min Range: -1.4928

Max Act: 0.9880. Min Act: -0.0000

Data Index: 1444858 (The Pile)

Max Activating Token Index: 357

Text #11

Max Range: 1.4928. Min Range: -1.4928

Max Act: 0.9708. Min Act: -0.0000

Data Index: 1279404 (The Pile)

Max Activating Token Index: 891

Text #12

Max Range: 1.4928. Min Range: -1.4928

Max Act: 0.9798. Min Act: -0.0000

Data Index: 1137522 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 1.4928. Min Range: -1.4928

Max Act: 0.9649. Min Act: 0.0000

Data Index: 530720 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 1.4928. Min Range: -1.4928

Max Act: 0.9332. Min Act: 0.0000

Data Index: 344509 (The Pile)

Max Activating Token Index: 561

Text #15

Max Range: 1.4928. Min Range: -1.4928

Max Act: 0.8214. Min Act: -0.0000

Data Index: 199381 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 1.4928. Min Range: -1.4928

Max Act: 0.8663. Min Act: -0.0000

Data Index: 353269 (The Pile)

Max Activating Token Index: 564

Text #17

Max Range: 1.4928. Min Range: -1.4928

Max Act: 0.9703. Min Act: -0.0000

Data Index: 165239 (The Pile)

Max Activating Token Index: 401

Text #18

Max Range: 1.4928. Min Range: -1.4928

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1845579 (The Pile)

Max Activating Token Index: 732

Text #19

Max Range: 1.4928. Min Range: -1.4928

Max Act: 0.9072. Min Act: -0.0000

Data Index: 1358398 (The Pile)

Max Activating Token Index: 247