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

Dataset: The Pile

Neuron 3004 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: 0.5006. Min Range: -0.5006

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1213675 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4468. Min Act: -0.0000

Data Index: 1723944 (The Pile)

Max Activating Token Index: 740

Text #2

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1359462 (The Pile)

Max Activating Token Index: 520

Text #3

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1500491 (The Pile)

Max Activating Token Index: 486

Text #4

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3665. Min Act: -0.0000

Data Index: 465538 (The Pile)

Max Activating Token Index: 988

Text #5

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3898. Min Act: -0.0000

Data Index: 1864811 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3626. Min Act: -0.0000

Data Index: 417332 (The Pile)

Max Activating Token Index: 741

Text #7

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3798. Min Act: -0.0000

Data Index: 553905 (The Pile)

Max Activating Token Index: 320

Text #8

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3822. Min Act: -0.0000

Data Index: 1112099 (The Pile)

Max Activating Token Index: 260

Text #9

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.4021. Min Act: -0.0000

Data Index: 1765951 (The Pile)

Max Activating Token Index: 216

Text #10

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3877. Min Act: -0.0000

Data Index: 682235 (The Pile)

Max Activating Token Index: 317

Text #11

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1014123 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3978. Min Act: -0.0000

Data Index: 229342 (The Pile)

Max Activating Token Index: 570

Text #13

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3420. Min Act: -0.0000

Data Index: 1843776 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3710. Min Act: -0.0000

Data Index: 1491789 (The Pile)

Max Activating Token Index: 638

Text #15

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3311. Min Act: -0.0000

Data Index: 75807 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3658. Min Act: -0.0000

Data Index: 1382632 (The Pile)

Max Activating Token Index: 757

Text #17

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1069 (The Pile)

Max Activating Token Index: 15

Text #18

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1868352 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 0.5006. Min Range: -0.5006

Max Act: 0.3720. Min Act: -0.0000

Data Index: 1529024 (The Pile)

Max Activating Token Index: 1018