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

Dataset: The Pile

Neuron 3538 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1152019 (The Pile)

Max Activating Token Index: 2

Text #1

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1330718 (The Pile)

Max Activating Token Index: 2

Text #2

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0971. Min Act: -0.0000

Data Index: 208113 (The Pile)

Max Activating Token Index: 157

Text #3

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0912. Min Act: 0.0000

Data Index: 1278581 (The Pile)

Max Activating Token Index: 4

Text #4

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0893. Min Act: 0.0000

Data Index: 1367908 (The Pile)

Max Activating Token Index: 332

Text #5

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0872. Min Act: 0.0000

Data Index: 370087 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1739985 (The Pile)

Max Activating Token Index: 528

Text #7

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0872. Min Act: -0.0000

Data Index: 967999 (The Pile)

Max Activating Token Index: 921

Text #8

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0869. Min Act: -0.0000

Data Index: 201071 (The Pile)

Max Activating Token Index: 218

Text #9

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0862. Min Act: 0.0000

Data Index: 1655103 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0855. Min Act: -0.0000

Data Index: 832053 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0830. Min Act: 0.0000

Data Index: 962265 (The Pile)

Max Activating Token Index: 662

Text #12

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0830. Min Act: 0.0000

Data Index: 1906617 (The Pile)

Max Activating Token Index: 190

Text #13

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0826. Min Act: -0.0000

Data Index: 969304 (The Pile)

Max Activating Token Index: 834

Text #14

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0790. Min Act: 0.0000

Data Index: 129128 (The Pile)

Max Activating Token Index: 642

Text #15

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0844. Min Act: 0.0001

Data Index: 561671 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0812. Min Act: -0.0000

Data Index: 673521 (The Pile)

Max Activating Token Index: 742

Text #17

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0804. Min Act: 0.0000

Data Index: 1359335 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0800. Min Act: 0.0000

Data Index: 1947380 (The Pile)

Max Activating Token Index: 774

Text #19

Max Range: 0.1170. Min Range: -0.1170

Max Act: 0.0800. Min Act: 0.0000

Data Index: 1480736 (The Pile)

Max Activating Token Index: 30