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

Dataset: The Pile

Neuron 4067 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: 0.4823. Min Range: -0.4823

Max Act: 0.4746. Min Act: -0.0000

Data Index: 952660 (The Pile)

Max Activating Token Index: 659

Text #1

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1231559 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1668399 (The Pile)

Max Activating Token Index: 494

Text #3

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3855. Min Act: -0.0000

Data Index: 3433 (The Pile)

Max Activating Token Index: 947

Text #4

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3863. Min Act: -0.0000

Data Index: 164869 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4183. Min Act: -0.0000

Data Index: 230953 (The Pile)

Max Activating Token Index: 331

Text #6

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4374. Min Act: -0.0000

Data Index: 224388 (The Pile)

Max Activating Token Index: 663

Text #7

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4010. Min Act: -0.0000

Data Index: 1582494 (The Pile)

Max Activating Token Index: 504

Text #8

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3851. Min Act: -0.0000

Data Index: 459256 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3889. Min Act: -0.0000

Data Index: 1666365 (The Pile)

Max Activating Token Index: 114

Text #10

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4083. Min Act: -0.0000

Data Index: 1027655 (The Pile)

Max Activating Token Index: 671

Text #11

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4005. Min Act: -0.0000

Data Index: 129358 (The Pile)

Max Activating Token Index: 166

Text #12

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1598275 (The Pile)

Max Activating Token Index: 300

Text #13

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1566362 (The Pile)

Max Activating Token Index: 750

Text #14

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3975. Min Act: -0.0000

Data Index: 1666660 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3762. Min Act: -0.0000

Data Index: 585073 (The Pile)

Max Activating Token Index: 420

Text #16

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1604373 (The Pile)

Max Activating Token Index: 130

Text #17

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3802. Min Act: -0.0000

Data Index: 788017 (The Pile)

Max Activating Token Index: 257

Text #18

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3662. Min Act: -0.0000

Data Index: 56286 (The Pile)

Max Activating Token Index: 235

Text #19

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1423604 (The Pile)

Max Activating Token Index: 102