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

Dataset: The Pile

Neuron 470 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2560. Min Range: -3.2560

Max Act: 3.1401. Min Act: -0.0000

Data Index: 220793 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 3.2560. Min Range: -3.2560

Max Act: 3.2560. Min Act: -0.0000

Data Index: 944396 (The Pile)

Max Activating Token Index: 740

Text #2

Max Range: 3.2560. Min Range: -3.2560

Max Act: 3.0933. Min Act: -0.0000

Data Index: 1495780 (The Pile)

Max Activating Token Index: 571

Text #3

Max Range: 3.2560. Min Range: -3.2560

Max Act: 2.9291. Min Act: -0.0000

Data Index: 1565200 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 3.2560. Min Range: -3.2560

Max Act: 2.2578. Min Act: -0.0000

Data Index: 1560240 (The Pile)

Max Activating Token Index: 726

Text #5

Max Range: 3.2560. Min Range: -3.2560

Max Act: 3.0224. Min Act: -0.0000

Data Index: 1706823 (The Pile)

Max Activating Token Index: 466

Text #6

Max Range: 3.2560. Min Range: -3.2560

Max Act: 2.5996. Min Act: -0.0000

Data Index: 1318054 (The Pile)

Max Activating Token Index: 759

Text #7

Max Range: 3.2560. Min Range: -3.2560

Max Act: 2.9641. Min Act: -0.0000

Data Index: 43322 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 3.2560. Min Range: -3.2560

Max Act: 2.7096. Min Act: -0.0000

Data Index: 1933043 (The Pile)

Max Activating Token Index: 904

Text #9

Max Range: 3.2560. Min Range: -3.2560

Max Act: 2.6636. Min Act: -0.0000

Data Index: 443050 (The Pile)

Max Activating Token Index: 719

Text #10

Max Range: 3.2560. Min Range: -3.2560

Max Act: 2.6828. Min Act: -0.0000

Data Index: 1403089 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 3.2560. Min Range: -3.2560

Max Act: 2.9514. Min Act: -0.0000

Data Index: 1578726 (The Pile)

Max Activating Token Index: 666

Text #12

Max Range: 3.2560. Min Range: -3.2560

Max Act: 2.9064. Min Act: -0.0000

Data Index: 494065 (The Pile)

Max Activating Token Index: 913

Text #13

Max Range: 3.2560. Min Range: -3.2560

Max Act: 2.2801. Min Act: -0.0000

Data Index: 1304163 (The Pile)

Max Activating Token Index: 981

Text #14

Max Range: 3.2560. Min Range: -3.2560

Max Act: 3.0602. Min Act: -0.0000

Data Index: 967076 (The Pile)

Max Activating Token Index: 561

Text #15

Max Range: 3.2560. Min Range: -3.2560

Max Act: 2.9442. Min Act: -0.0000

Data Index: 292957 (The Pile)

Max Activating Token Index: 512

Text #16

Max Range: 3.2560. Min Range: -3.2560

Max Act: 2.3525. Min Act: -0.0000

Data Index: 1827675 (The Pile)

Max Activating Token Index: 926

Text #17

Max Range: 3.2560. Min Range: -3.2560

Max Act: 3.1748. Min Act: -0.0000

Data Index: 1043840 (The Pile)

Max Activating Token Index: 284

Text #18

Max Range: 3.2560. Min Range: -3.2560

Max Act: 2.7425. Min Act: -0.0000

Data Index: 1799694 (The Pile)

Max Activating Token Index: 700

Text #19

Max Range: 3.2560. Min Range: -3.2560

Max Act: 2.5500. Min Act: -0.0000

Data Index: 405354 (The Pile)

Max Activating Token Index: 984