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

Dataset: The Pile

Neuron 4655 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.6974. Min Range: -3.6974

Max Act: 3.6974. Min Act: -0.0000

Data Index: 1574074 (The Pile)

Max Activating Token Index: 905

Text #1

Max Range: 3.6974. Min Range: -3.6974

Max Act: 2.2482. Min Act: -0.0000

Data Index: 153586 (The Pile)

Max Activating Token Index: 14

Text #2

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.8912. Min Act: -0.0000

Data Index: 1799761 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.8400. Min Act: -0.0000

Data Index: 799916 (The Pile)

Max Activating Token Index: 789

Text #4

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.9289. Min Act: -0.0000

Data Index: 980279 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.9200. Min Act: -0.0000

Data Index: 279659 (The Pile)

Max Activating Token Index: 976

Text #6

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.8102. Min Act: -0.0000

Data Index: 1870273 (The Pile)

Max Activating Token Index: 633

Text #7

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.8965. Min Act: -0.0000

Data Index: 912855 (The Pile)

Max Activating Token Index: 814

Text #8

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.6597. Min Act: -0.0000

Data Index: 1719082 (The Pile)

Max Activating Token Index: 844

Text #9

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.9455. Min Act: -0.0000

Data Index: 1477953 (The Pile)

Max Activating Token Index: 876

Text #10

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.5945. Min Act: -0.0000

Data Index: 1675400 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.8868. Min Act: -0.0000

Data Index: 643500 (The Pile)

Max Activating Token Index: 829

Text #12

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.4510. Min Act: -0.0000

Data Index: 955090 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.7532. Min Act: -0.0000

Data Index: 1479642 (The Pile)

Max Activating Token Index: 975

Text #14

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.8468. Min Act: -0.0000

Data Index: 610046 (The Pile)

Max Activating Token Index: 844

Text #15

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.5722. Min Act: -0.0000

Data Index: 834237 (The Pile)

Max Activating Token Index: 907

Text #16

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.6784. Min Act: -0.0000

Data Index: 1475508 (The Pile)

Max Activating Token Index: 754

Text #17

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.7282. Min Act: -0.0000

Data Index: 1807050 (The Pile)

Max Activating Token Index: 17

Text #18

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.8613. Min Act: -0.0000

Data Index: 661466 (The Pile)

Max Activating Token Index: 778

Text #19

Max Range: 3.6974. Min Range: -3.6974

Max Act: 1.6633. Min Act: -0.0000

Data Index: 631489 (The Pile)

Max Activating Token Index: 517