Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1661 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1563364 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.7288. Min Act: -0.0000

Data Index: 831163 (The Pile)

Max Activating Token Index: 834

Text #2

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1537888 (The Pile)

Max Activating Token Index: 794

Text #3

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6661. Min Act: -0.0000

Data Index: 745117 (The Pile)

Max Activating Token Index: 984

Text #4

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6674. Min Act: -0.0000

Data Index: 483590 (The Pile)

Max Activating Token Index: 375

Text #5

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6971. Min Act: -0.0000

Data Index: 461292 (The Pile)

Max Activating Token Index: 508

Text #6

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1898304 (The Pile)

Max Activating Token Index: 964

Text #7

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6900. Min Act: -0.0000

Data Index: 499074 (The Pile)

Max Activating Token Index: 378

Text #8

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6630. Min Act: 0.0000

Data Index: 1162109 (The Pile)

Max Activating Token Index: 884

Text #9

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1057995 (The Pile)

Max Activating Token Index: 770

Text #10

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1356035 (The Pile)

Max Activating Token Index: 852

Text #11

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6897. Min Act: -0.0000

Data Index: 1299253 (The Pile)

Max Activating Token Index: 834

Text #12

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6701. Min Act: -0.0000

Data Index: 139127 (The Pile)

Max Activating Token Index: 532

Text #13

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6621. Min Act: -0.0000

Data Index: 403290 (The Pile)

Max Activating Token Index: 842

Text #14

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1934852 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6601. Min Act: -0.0000

Data Index: 365775 (The Pile)

Max Activating Token Index: 663

Text #16

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6600. Min Act: -0.0000

Data Index: 1215186 (The Pile)

Max Activating Token Index: 1011

Text #17

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1032781 (The Pile)

Max Activating Token Index: 948

Text #18

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1872513 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 0.7692. Min Range: -0.7692

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1016332 (The Pile)

Max Activating Token Index: 682