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

Dataset: The Pile

Neuron 4451 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: 0.4922. Min Range: -0.4922

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1930341 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.4381. Min Act: -0.0000

Data Index: 1395557 (The Pile)

Max Activating Token Index: 522

Text #2

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3715. Min Act: -0.0000

Data Index: 667789 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3542. Min Act: -0.0000

Data Index: 1835109 (The Pile)

Max Activating Token Index: 279

Text #4

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3850. Min Act: -0.0000

Data Index: 1480992 (The Pile)

Max Activating Token Index: 343

Text #5

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1350906 (The Pile)

Max Activating Token Index: 720

Text #6

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3419. Min Act: -0.0000

Data Index: 539126 (The Pile)

Max Activating Token Index: 233

Text #7

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3523. Min Act: -0.0000

Data Index: 179079 (The Pile)

Max Activating Token Index: 680

Text #8

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1046725 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3813. Min Act: -0.0000

Data Index: 295552 (The Pile)

Max Activating Token Index: 858

Text #10

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3247. Min Act: -0.0000

Data Index: 857713 (The Pile)

Max Activating Token Index: 528

Text #11

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3370. Min Act: -0.0000

Data Index: 1927246 (The Pile)

Max Activating Token Index: 993

Text #12

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1534329 (The Pile)

Max Activating Token Index: 974

Text #13

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1710755 (The Pile)

Max Activating Token Index: 278

Text #14

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1004233 (The Pile)

Max Activating Token Index: 631

Text #15

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2966. Min Act: -0.0000

Data Index: 1950378 (The Pile)

Max Activating Token Index: 390

Text #16

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1405004 (The Pile)

Max Activating Token Index: 186

Text #17

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1154313 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2747. Min Act: -0.0000

Data Index: 625640 (The Pile)

Max Activating Token Index: 895

Text #19

Max Range: 0.4922. Min Range: -0.4922

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1421083 (The Pile)

Max Activating Token Index: 898