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

Dataset: The Pile

Neuron 5014 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1127005 (The Pile)

Max Activating Token Index: 337

Text #1

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2158. Min Act: -0.0000

Data Index: 760090 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1409665 (The Pile)

Max Activating Token Index: 389

Text #3

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1270887 (The Pile)

Max Activating Token Index: 19

Text #4

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1969. Min Act: 0.0000

Data Index: 520448 (The Pile)

Max Activating Token Index: 836

Text #5

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1690932 (The Pile)

Max Activating Token Index: 475

Text #6

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1881. Min Act: -0.0000

Data Index: 1910978 (The Pile)

Max Activating Token Index: 509

Text #7

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1814. Min Act: -0.0000

Data Index: 468812 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1246481 (The Pile)

Max Activating Token Index: 533

Text #9

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1840300 (The Pile)

Max Activating Token Index: 806

Text #10

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1742. Min Act: -0.0000

Data Index: 626374 (The Pile)

Max Activating Token Index: 875

Text #11

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1938492 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1814932 (The Pile)

Max Activating Token Index: 32

Text #13

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1593. Min Act: -0.0000

Data Index: 1874003 (The Pile)

Max Activating Token Index: 125

Text #14

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1658. Min Act: -0.0000

Data Index: 419483 (The Pile)

Max Activating Token Index: 1001

Text #15

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1612. Min Act: 0.0000

Data Index: 1719312 (The Pile)

Max Activating Token Index: 103

Text #16

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1605. Min Act: -0.0000

Data Index: 1016833 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1575. Min Act: -0.0000

Data Index: 498302 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1476. Min Act: -0.0000

Data Index: 228245 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1152321 (The Pile)

Max Activating Token Index: 1010