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

Dataset: The Pile

Neuron 2866 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: 1.4982. Min Range: -1.4982

Max Act: 1.4982. Min Act: -0.0000

Data Index: 984598 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.3564. Min Act: -0.0000

Data Index: 1065033 (The Pile)

Max Activating Token Index: 236

Text #2

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.3659. Min Act: -0.0000

Data Index: 483200 (The Pile)

Max Activating Token Index: 545

Text #3

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.2422. Min Act: -0.0000

Data Index: 791087 (The Pile)

Max Activating Token Index: 996

Text #4

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.2759. Min Act: -0.0000

Data Index: 938831 (The Pile)

Max Activating Token Index: 260

Text #5

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.1402. Min Act: -0.0000

Data Index: 982108 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.1814. Min Act: -0.0000

Data Index: 446069 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.1775. Min Act: -0.0000

Data Index: 1394313 (The Pile)

Max Activating Token Index: 881

Text #8

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.2099. Min Act: -0.0000

Data Index: 656085 (The Pile)

Max Activating Token Index: 881

Text #9

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.1778. Min Act: -0.0000

Data Index: 709702 (The Pile)

Max Activating Token Index: 201

Text #10

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.3144. Min Act: -0.0000

Data Index: 688366 (The Pile)

Max Activating Token Index: 987

Text #11

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.0368. Min Act: -0.0000

Data Index: 1117284 (The Pile)

Max Activating Token Index: 755

Text #12

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.0840. Min Act: -0.0000

Data Index: 632451 (The Pile)

Max Activating Token Index: 455

Text #13

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.1585. Min Act: -0.0000

Data Index: 1308515 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.0872. Min Act: -0.0000

Data Index: 1035588 (The Pile)

Max Activating Token Index: 101

Text #15

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.0363. Min Act: -0.0000

Data Index: 1290786 (The Pile)

Max Activating Token Index: 987

Text #16

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.0557. Min Act: -0.0000

Data Index: 620302 (The Pile)

Max Activating Token Index: 723

Text #17

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.0262. Min Act: -0.0000

Data Index: 1263822 (The Pile)

Max Activating Token Index: 708

Text #18

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.1267. Min Act: -0.0000

Data Index: 1691097 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 1.4982. Min Range: -1.4982

Max Act: 1.0610. Min Act: -0.0000

Data Index: 1889016 (The Pile)

Max Activating Token Index: 89