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

Dataset: The Pile

Neuron 4935 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.3680. Min Act: -0.0000

Data Index: 1812937 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.2910. Min Act: -0.0000

Data Index: 1366496 (The Pile)

Max Activating Token Index: 366

Text #2

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.2827. Min Act: -0.0000

Data Index: 1878341 (The Pile)

Max Activating Token Index: 271

Text #3

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.2638. Min Act: -0.0000

Data Index: 706117 (The Pile)

Max Activating Token Index: 36

Text #4

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.3365. Min Act: -0.0000

Data Index: 724909 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.2829. Min Act: -0.0000

Data Index: 1054952 (The Pile)

Max Activating Token Index: 32

Text #6

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.2102. Min Act: -0.0000

Data Index: 998980 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.0936. Min Act: -0.0000

Data Index: 910792 (The Pile)

Max Activating Token Index: 603

Text #8

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1204250 (The Pile)

Max Activating Token Index: 369

Text #9

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1052. Min Act: -0.0000

Data Index: 1866275 (The Pile)

Max Activating Token Index: 337

Text #10

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1920. Min Act: -0.0000

Data Index: 166507 (The Pile)

Max Activating Token Index: 692

Text #11

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.0831. Min Act: -0.0000

Data Index: 252411 (The Pile)

Max Activating Token Index: 365

Text #12

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.2156. Min Act: -0.0000

Data Index: 368591 (The Pile)

Max Activating Token Index: 634

Text #13

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1467539 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1367005 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.0937. Min Act: -0.0000

Data Index: 615635 (The Pile)

Max Activating Token Index: 426

Text #16

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1618. Min Act: -0.0000

Data Index: 1769564 (The Pile)

Max Activating Token Index: 11

Text #17

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1302. Min Act: -0.0000

Data Index: 480417 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1258. Min Act: -0.0000

Data Index: 307744 (The Pile)

Max Activating Token Index: 374

Text #19

Max Range: 1.3680. Min Range: -1.3680

Max Act: 1.1252. Min Act: -0.0000

Data Index: 652133 (The Pile)

Max Activating Token Index: 617