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

Dataset: The Pile

Neuron 3154 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: 1.9751. Min Range: -1.9751

Max Act: 1.9751. Min Act: -0.0000

Data Index: 698225 (The Pile)

Max Activating Token Index: 1000

Text #1

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.7757. Min Act: -0.0000

Data Index: 1110826 (The Pile)

Max Activating Token Index: 42

Text #2

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.6211. Min Act: -0.0000

Data Index: 97500 (The Pile)

Max Activating Token Index: 742

Text #3

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.7990. Min Act: -0.0000

Data Index: 517426 (The Pile)

Max Activating Token Index: 123

Text #4

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.5993. Min Act: -0.0000

Data Index: 167215 (The Pile)

Max Activating Token Index: 14

Text #5

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.6747. Min Act: -0.0000

Data Index: 449872 (The Pile)

Max Activating Token Index: 193

Text #6

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.4913. Min Act: -0.0000

Data Index: 1449879 (The Pile)

Max Activating Token Index: 320

Text #7

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.5715. Min Act: -0.0000

Data Index: 1174680 (The Pile)

Max Activating Token Index: 81

Text #8

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.5626. Min Act: -0.0000

Data Index: 1338949 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.5509. Min Act: -0.0000

Data Index: 798730 (The Pile)

Max Activating Token Index: 577

Text #10

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.4620. Min Act: -0.0000

Data Index: 1003743 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.5364. Min Act: -0.0000

Data Index: 1039830 (The Pile)

Max Activating Token Index: 515

Text #12

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.4504. Min Act: -0.0000

Data Index: 579509 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.4563. Min Act: -0.0000

Data Index: 127050 (The Pile)

Max Activating Token Index: 22

Text #14

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.3636. Min Act: -0.0000

Data Index: 917204 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.4096. Min Act: -0.0000

Data Index: 696112 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.2459. Min Act: -0.0000

Data Index: 822537 (The Pile)

Max Activating Token Index: 523

Text #17

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.3907. Min Act: -0.0000

Data Index: 415869 (The Pile)

Max Activating Token Index: 491

Text #18

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.3127. Min Act: -0.0000

Data Index: 1496632 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 1.9751. Min Range: -1.9751

Max Act: 1.3794. Min Act: -0.0000

Data Index: 1645207 (The Pile)

Max Activating Token Index: 166