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

Dataset: The Pile

Neuron 2503 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: 0.1076. Min Range: -0.1076

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1815410 (The Pile)

Max Activating Token Index: 326

Text #1

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0988. Min Act: -0.0000

Data Index: 1904298 (The Pile)

Max Activating Token Index: 68

Text #2

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0842. Min Act: -0.0000

Data Index: 401696 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0660. Min Act: -0.0000

Data Index: 856089 (The Pile)

Max Activating Token Index: 717

Text #4

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1076. Min Act: -0.0000

Data Index: 720223 (The Pile)

Max Activating Token Index: 777

Text #5

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0919. Min Act: -0.0000

Data Index: 728234 (The Pile)

Max Activating Token Index: 299

Text #6

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1461831 (The Pile)

Max Activating Token Index: 250

Text #7

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0866. Min Act: -0.0000

Data Index: 324260 (The Pile)

Max Activating Token Index: 621

Text #8

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0988. Min Act: -0.0000

Data Index: 262028 (The Pile)

Max Activating Token Index: 372

Text #9

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1128341 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0830. Min Act: -0.0000

Data Index: 753312 (The Pile)

Max Activating Token Index: 106

Text #11

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0855. Min Act: -0.0000

Data Index: 827662 (The Pile)

Max Activating Token Index: 569

Text #12

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0727. Min Act: -0.0000

Data Index: 1310764 (The Pile)

Max Activating Token Index: 221

Text #13

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0780. Min Act: -0.0000

Data Index: 64659 (The Pile)

Max Activating Token Index: 522

Text #14

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0673. Min Act: -0.0000

Data Index: 620050 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1612704 (The Pile)

Max Activating Token Index: 630

Text #16

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0777. Min Act: -0.0000

Data Index: 1098370 (The Pile)

Max Activating Token Index: 513

Text #17

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1281079 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0727. Min Act: -0.0000

Data Index: 1657417 (The Pile)

Max Activating Token Index: 456

Text #19

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1749175 (The Pile)

Max Activating Token Index: 895