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

Dataset: The Pile

Neuron 2595 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.3853. Min Act: -0.0000

Data Index: 1357451 (The Pile)

Max Activating Token Index: 846

Text #1

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.1907. Min Act: -0.0000

Data Index: 1223542 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.0263. Min Act: -0.0000

Data Index: 1185983 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 4.3853. Min Range: -4.3853

Max Act: 3.8904. Min Act: -0.0000

Data Index: 1258792 (The Pile)

Max Activating Token Index: 913

Text #4

Max Range: 4.3853. Min Range: -4.3853

Max Act: 3.7643. Min Act: -0.0000

Data Index: 713063 (The Pile)

Max Activating Token Index: 765

Text #5

Max Range: 4.3853. Min Range: -4.3853

Max Act: 3.8656. Min Act: -0.0000

Data Index: 1277887 (The Pile)

Max Activating Token Index: 137

Text #6

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.1538. Min Act: -0.0000

Data Index: 102342 (The Pile)

Max Activating Token Index: 590

Text #7

Max Range: 4.3853. Min Range: -4.3853

Max Act: 3.7915. Min Act: -0.0000

Data Index: 1529706 (The Pile)

Max Activating Token Index: 298

Text #8

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.1144. Min Act: -0.0000

Data Index: 565720 (The Pile)

Max Activating Token Index: 182

Text #9

Max Range: 4.3853. Min Range: -4.3853

Max Act: 3.5967. Min Act: -0.0000

Data Index: 1045012 (The Pile)

Max Activating Token Index: 546

Text #10

Max Range: 4.3853. Min Range: -4.3853

Max Act: 3.6708. Min Act: -0.0000

Data Index: 83693 (The Pile)

Max Activating Token Index: 913

Text #11

Max Range: 4.3853. Min Range: -4.3853

Max Act: 3.7810. Min Act: -0.0000

Data Index: 1677756 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 4.3853. Min Range: -4.3853

Max Act: 3.5958. Min Act: -0.0000

Data Index: 1566224 (The Pile)

Max Activating Token Index: 148

Text #13

Max Range: 4.3853. Min Range: -4.3853

Max Act: 4.0823. Min Act: -0.0000

Data Index: 56575 (The Pile)

Max Activating Token Index: 61

Text #14

Max Range: 4.3853. Min Range: -4.3853

Max Act: 3.5641. Min Act: -0.0000

Data Index: 1731603 (The Pile)

Max Activating Token Index: 682

Text #15

Max Range: 4.3853. Min Range: -4.3853

Max Act: 3.9082. Min Act: -0.0000

Data Index: 270040 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 4.3853. Min Range: -4.3853

Max Act: 3.3973. Min Act: -0.0000

Data Index: 1878731 (The Pile)

Max Activating Token Index: 515

Text #17

Max Range: 4.3853. Min Range: -4.3853

Max Act: 3.9936. Min Act: -0.0000

Data Index: 1691009 (The Pile)

Max Activating Token Index: 759

Text #18

Max Range: 4.3853. Min Range: -4.3853

Max Act: 3.4712. Min Act: -0.0000

Data Index: 1118047 (The Pile)

Max Activating Token Index: 647

Text #19

Max Range: 4.3853. Min Range: -4.3853

Max Act: 3.6428. Min Act: -0.0000

Data Index: 1263191 (The Pile)

Max Activating Token Index: 296