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

Dataset: The Pile

Neuron 3935 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: 1.3367. Min Range: -1.3367

Max Act: 1.3367. Min Act: -0.0000

Data Index: 921845 (The Pile)

Max Activating Token Index: 123

Text #1

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.0741. Min Act: -0.0000

Data Index: 316605 (The Pile)

Max Activating Token Index: 406

Text #2

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.1414. Min Act: -0.0000

Data Index: 1998032 (The Pile)

Max Activating Token Index: 342

Text #3

Max Range: 1.3367. Min Range: -1.3367

Max Act: 1.0790. Min Act: -0.0000

Data Index: 1073250 (The Pile)

Max Activating Token Index: 654

Text #4

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1928462 (The Pile)

Max Activating Token Index: 916

Text #5

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9972. Min Act: -0.0000

Data Index: 1897896 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9657. Min Act: -0.0000

Data Index: 964693 (The Pile)

Max Activating Token Index: 326

Text #7

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1455406 (The Pile)

Max Activating Token Index: 121

Text #8

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9731. Min Act: -0.0000

Data Index: 1046644 (The Pile)

Max Activating Token Index: 73

Text #9

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9409. Min Act: -0.0000

Data Index: 1701515 (The Pile)

Max Activating Token Index: 643

Text #10

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9102. Min Act: -0.0000

Data Index: 101930 (The Pile)

Max Activating Token Index: 789

Text #11

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1902294 (The Pile)

Max Activating Token Index: 416

Text #12

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9117. Min Act: -0.0000

Data Index: 976907 (The Pile)

Max Activating Token Index: 278

Text #13

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1293984 (The Pile)

Max Activating Token Index: 567

Text #14

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.9519. Min Act: -0.0000

Data Index: 1794787 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.8906. Min Act: -0.0000

Data Index: 1971592 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.8303. Min Act: -0.0000

Data Index: 446137 (The Pile)

Max Activating Token Index: 131

Text #17

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.8303. Min Act: -0.0000

Data Index: 59803 (The Pile)

Max Activating Token Index: 220

Text #18

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1066787 (The Pile)

Max Activating Token Index: 281

Text #19

Max Range: 1.3367. Min Range: -1.3367

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1830712 (The Pile)

Max Activating Token Index: 1003