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

Dataset: The Pile

Neuron 4133 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.5680. Min Act: -0.0000

Data Index: 1139464 (The Pile)

Max Activating Token Index: 150

Text #1

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.4508. Min Act: -0.0000

Data Index: 1532328 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.2545. Min Act: -0.0000

Data Index: 1928830 (The Pile)

Max Activating Token Index: 466

Text #3

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.1690. Min Act: -0.0000

Data Index: 1617761 (The Pile)

Max Activating Token Index: 699

Text #4

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.2105. Min Act: -0.0000

Data Index: 19537 (The Pile)

Max Activating Token Index: 936

Text #5

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.0469. Min Act: -0.0000

Data Index: 1201590 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.0448. Min Act: -0.0000

Data Index: 1695514 (The Pile)

Max Activating Token Index: 694

Text #7

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.0298. Min Act: -0.0000

Data Index: 1795438 (The Pile)

Max Activating Token Index: 477

Text #8

Max Range: 1.5680. Min Range: -1.5680

Max Act: 1.0320. Min Act: -0.0000

Data Index: 1066446 (The Pile)

Max Activating Token Index: 320

Text #9

Max Range: 1.5680. Min Range: -1.5680

Max Act: 0.8784. Min Act: -0.0000

Data Index: 858064 (The Pile)

Max Activating Token Index: 752

Text #10

Max Range: 1.5680. Min Range: -1.5680

Max Act: 0.9956. Min Act: -0.0000

Data Index: 322636 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 1.5680. Min Range: -1.5680

Max Act: 0.9673. Min Act: -0.0000

Data Index: 1755977 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 1.5680. Min Range: -1.5680

Max Act: 0.9823. Min Act: -0.0000

Data Index: 481745 (The Pile)

Max Activating Token Index: 847

Text #13

Max Range: 1.5680. Min Range: -1.5680

Max Act: 0.9906. Min Act: -0.0000

Data Index: 836973 (The Pile)

Max Activating Token Index: 315

Text #14

Max Range: 1.5680. Min Range: -1.5680

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1618788 (The Pile)

Max Activating Token Index: 148

Text #15

Max Range: 1.5680. Min Range: -1.5680

Max Act: 0.9414. Min Act: -0.0000

Data Index: 239159 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 1.5680. Min Range: -1.5680

Max Act: 0.9045. Min Act: -0.0000

Data Index: 1707148 (The Pile)

Max Activating Token Index: 369

Text #17

Max Range: 1.5680. Min Range: -1.5680

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1662846 (The Pile)

Max Activating Token Index: 538

Text #18

Max Range: 1.5680. Min Range: -1.5680

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1832935 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 1.5680. Min Range: -1.5680

Max Act: 0.9274. Min Act: -0.0000

Data Index: 1608564 (The Pile)

Max Activating Token Index: 824