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

Dataset: The Pile

Neuron 2275 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: 0.4663. Min Range: -0.4663

Max Act: 0.4481. Min Act: -0.0000

Data Index: 734403 (The Pile)

Max Activating Token Index: 773

Text #1

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1124165 (The Pile)

Max Activating Token Index: 164

Text #2

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4663. Min Act: -0.0000

Data Index: 600645 (The Pile)

Max Activating Token Index: 183

Text #3

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4188. Min Act: -0.0000

Data Index: 251276 (The Pile)

Max Activating Token Index: 234

Text #4

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1951185 (The Pile)

Max Activating Token Index: 259

Text #5

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3851. Min Act: -0.0000

Data Index: 1922149 (The Pile)

Max Activating Token Index: 177

Text #6

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1338046 (The Pile)

Max Activating Token Index: 35

Text #7

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1674934 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3846. Min Act: -0.0000

Data Index: 1098764 (The Pile)

Max Activating Token Index: 650

Text #9

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3686. Min Act: -0.0000

Data Index: 1358330 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3292. Min Act: -0.0000

Data Index: 1650843 (The Pile)

Max Activating Token Index: 744

Text #11

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3495. Min Act: -0.0000

Data Index: 1348017 (The Pile)

Max Activating Token Index: 521

Text #12

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1691491 (The Pile)

Max Activating Token Index: 892

Text #13

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1066965 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3898. Min Act: -0.0000

Data Index: 101319 (The Pile)

Max Activating Token Index: 622

Text #15

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3394. Min Act: -0.0000

Data Index: 1385363 (The Pile)

Max Activating Token Index: 706

Text #16

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3616. Min Act: -0.0000

Data Index: 65855 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1025823 (The Pile)

Max Activating Token Index: 212

Text #18

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3317. Min Act: -0.0000

Data Index: 383818 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 0.4663. Min Range: -0.4663

Max Act: 0.3342. Min Act: -0.0000

Data Index: 1639559 (The Pile)

Max Activating Token Index: 590