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

Dataset: The Pile

Neuron 3386 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: 1.3798. Min Range: -1.3798

Max Act: 1.3798. Min Act: -0.0000

Data Index: 848893 (The Pile)

Max Activating Token Index: 387

Text #1

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0457. Min Act: -0.0000

Data Index: 1163264 (The Pile)

Max Activating Token Index: 294

Text #2

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0080. Min Act: -0.0000

Data Index: 566085 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9425. Min Act: -0.0000

Data Index: 1627271 (The Pile)

Max Activating Token Index: 769

Text #4

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0073. Min Act: -0.0000

Data Index: 867219 (The Pile)

Max Activating Token Index: 332

Text #5

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9521. Min Act: -0.0000

Data Index: 139495 (The Pile)

Max Activating Token Index: 324

Text #6

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9284. Min Act: -0.0000

Data Index: 553135 (The Pile)

Max Activating Token Index: 361

Text #7

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9240. Min Act: -0.0000

Data Index: 1047506 (The Pile)

Max Activating Token Index: 204

Text #8

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1423705 (The Pile)

Max Activating Token Index: 881

Text #9

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1418133 (The Pile)

Max Activating Token Index: 191

Text #10

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1854061 (The Pile)

Max Activating Token Index: 806

Text #11

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8674. Min Act: -0.0000

Data Index: 986199 (The Pile)

Max Activating Token Index: 89

Text #12

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1700905 (The Pile)

Max Activating Token Index: 654

Text #13

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8884. Min Act: -0.0000

Data Index: 561833 (The Pile)

Max Activating Token Index: 486

Text #14

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1332146 (The Pile)

Max Activating Token Index: 952

Text #15

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.7863. Min Act: -0.0000

Data Index: 494290 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.7707. Min Act: -0.0000

Data Index: 868585 (The Pile)

Max Activating Token Index: 773

Text #17

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1781224 (The Pile)

Max Activating Token Index: 286

Text #18

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.6668. Min Act: -0.0000

Data Index: 1772920 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.7480. Min Act: -0.0000

Data Index: 1640342 (The Pile)

Max Activating Token Index: 699