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

Dataset: The Pile

Neuron 4764 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: 1.4397. Min Range: -1.4397

Max Act: 1.4397. Min Act: -0.0000

Data Index: 1703407 (The Pile)

Max Activating Token Index: 543

Text #1

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1729. Min Act: -0.0000

Data Index: 1863484 (The Pile)

Max Activating Token Index: 858

Text #2

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.2835. Min Act: -0.0000

Data Index: 1725652 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.2000. Min Act: -0.0000

Data Index: 1086039 (The Pile)

Max Activating Token Index: 439

Text #4

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.2689. Min Act: -0.0000

Data Index: 973458 (The Pile)

Max Activating Token Index: 304

Text #5

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1290. Min Act: -0.0000

Data Index: 196525 (The Pile)

Max Activating Token Index: 232

Text #6

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1680. Min Act: -0.0000

Data Index: 1463249 (The Pile)

Max Activating Token Index: 767

Text #7

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1508. Min Act: -0.0000

Data Index: 814026 (The Pile)

Max Activating Token Index: 331

Text #8

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.2705. Min Act: -0.0000

Data Index: 1990549 (The Pile)

Max Activating Token Index: 607

Text #9

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.0860. Min Act: -0.0000

Data Index: 781573 (The Pile)

Max Activating Token Index: 843

Text #10

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1908. Min Act: -0.0000

Data Index: 202446 (The Pile)

Max Activating Token Index: 142

Text #11

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1243. Min Act: -0.0000

Data Index: 598378 (The Pile)

Max Activating Token Index: 276

Text #12

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.0876. Min Act: -0.0000

Data Index: 107074 (The Pile)

Max Activating Token Index: 514

Text #13

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.2583. Min Act: -0.0000

Data Index: 585549 (The Pile)

Max Activating Token Index: 610

Text #14

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1390. Min Act: -0.0000

Data Index: 210321 (The Pile)

Max Activating Token Index: 607

Text #15

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.0810. Min Act: -0.0000

Data Index: 707598 (The Pile)

Max Activating Token Index: 314

Text #16

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.0719. Min Act: -0.0000

Data Index: 292698 (The Pile)

Max Activating Token Index: 465

Text #17

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.0903. Min Act: -0.0000

Data Index: 153622 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.0530. Min Act: -0.0000

Data Index: 1897884 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 1.4397. Min Range: -1.4397

Max Act: 1.1800. Min Act: -0.0000

Data Index: 141460 (The Pile)

Max Activating Token Index: 478