Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 672 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.3117. Min Act: -0.0000

Data Index: 699549 (The Pile)

Max Activating Token Index: 980

Text #1

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2621. Min Act: -0.0000

Data Index: 488060 (The Pile)

Max Activating Token Index: 532

Text #2

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2620. Min Act: -0.0000

Data Index: 1985948 (The Pile)

Max Activating Token Index: 740

Text #3

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2601. Min Act: -0.0000

Data Index: 594393 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1238674 (The Pile)

Max Activating Token Index: 838

Text #5

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2167. Min Act: -0.0000

Data Index: 1826734 (The Pile)

Max Activating Token Index: 896

Text #6

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.2028. Min Act: -0.0000

Data Index: 1717545 (The Pile)

Max Activating Token Index: 247

Text #7

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.1910. Min Act: -0.0000

Data Index: 660415 (The Pile)

Max Activating Token Index: 672

Text #8

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1594145 (The Pile)

Max Activating Token Index: 957

Text #9

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1707081 (The Pile)

Max Activating Token Index: 846

Text #10

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1457160 (The Pile)

Max Activating Token Index: 997

Text #11

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1420643 (The Pile)

Max Activating Token Index: 590

Text #12

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.1648. Min Act: -0.0000

Data Index: 164159 (The Pile)

Max Activating Token Index: 361

Text #13

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1792649 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.1517. Min Act: -0.0000

Data Index: 733049 (The Pile)

Max Activating Token Index: 1020

Text #15

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1737255 (The Pile)

Max Activating Token Index: 557

Text #16

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.1418. Min Act: -0.0000

Data Index: 1151577 (The Pile)

Max Activating Token Index: 498

Text #17

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.1466. Min Act: -0.0000

Data Index: 1277453 (The Pile)

Max Activating Token Index: 988

Text #18

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.1604. Min Act: -0.0000

Data Index: 224665 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 0.3117. Min Range: -0.3117

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1779977 (The Pile)

Max Activating Token Index: 722