Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 475 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1218530 (The Pile)

Max Activating Token Index: 163

Text #1

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1028. Min Act: -0.0000

Data Index: 810630 (The Pile)

Max Activating Token Index: 486

Text #2

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.1010. Min Act: -0.0000

Data Index: 246128 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1901370 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0916. Min Act: -0.0000

Data Index: 418568 (The Pile)

Max Activating Token Index: 127

Text #5

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1936008 (The Pile)

Max Activating Token Index: 187

Text #6

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0977. Min Act: -0.0000

Data Index: 554284 (The Pile)

Max Activating Token Index: 547

Text #7

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0860. Min Act: -0.0000

Data Index: 804478 (The Pile)

Max Activating Token Index: 180

Text #8

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0842. Min Act: -0.0000

Data Index: 893982 (The Pile)

Max Activating Token Index: 591

Text #9

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0858. Min Act: -0.0001

Data Index: 751240 (The Pile)

Max Activating Token Index: 779

Text #10

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1329237 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1529813 (The Pile)

Max Activating Token Index: 955

Text #12

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0860. Min Act: -0.0000

Data Index: 26880 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1879350 (The Pile)

Max Activating Token Index: 996

Text #14

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1896698 (The Pile)

Max Activating Token Index: 103

Text #15

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0825. Min Act: -0.0000

Data Index: 1674810 (The Pile)

Max Activating Token Index: 368

Text #16

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0853. Min Act: -0.0000

Data Index: 275380 (The Pile)

Max Activating Token Index: 742

Text #17

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0834. Min Act: -0.0000

Data Index: 1810152 (The Pile)

Max Activating Token Index: 190

Text #18

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0863. Min Act: -0.0000

Data Index: 833579 (The Pile)

Max Activating Token Index: 67

Text #19

Max Range: 0.1100. Min Range: -0.1100

Max Act: 0.0766. Min Act: -0.0000

Data Index: 196962 (The Pile)

Max Activating Token Index: 967