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

Dataset: The Pile

Neuron 5003 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.8030. Min Act: -0.0000

Data Index: 785930 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.4586. Min Act: -0.0000

Data Index: 680103 (The Pile)

Max Activating Token Index: 162

Text #2

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.6372. Min Act: -0.0000

Data Index: 63703 (The Pile)

Max Activating Token Index: 187

Text #3

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.7832. Min Act: -0.0000

Data Index: 114559 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.4915. Min Act: -0.0000

Data Index: 971060 (The Pile)

Max Activating Token Index: 228

Text #5

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.5673. Min Act: -0.0000

Data Index: 1470620 (The Pile)

Max Activating Token Index: 571

Text #6

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.5383. Min Act: -0.0000

Data Index: 535950 (The Pile)

Max Activating Token Index: 946

Text #7

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.5822. Min Act: -0.0000

Data Index: 1803785 (The Pile)

Max Activating Token Index: 814

Text #8

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.4275. Min Act: -0.0000

Data Index: 119510 (The Pile)

Max Activating Token Index: 899

Text #9

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.4630. Min Act: -0.0000

Data Index: 1379791 (The Pile)

Max Activating Token Index: 33

Text #10

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.5325. Min Act: -0.0000

Data Index: 352176 (The Pile)

Max Activating Token Index: 597

Text #11

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.5262. Min Act: -0.0000

Data Index: 1306923 (The Pile)

Max Activating Token Index: 914

Text #12

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.4104. Min Act: -0.0000

Data Index: 88260 (The Pile)

Max Activating Token Index: 711

Text #13

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.3228. Min Act: -0.0000

Data Index: 1305190 (The Pile)

Max Activating Token Index: 843

Text #14

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.3874. Min Act: -0.0000

Data Index: 1174565 (The Pile)

Max Activating Token Index: 649

Text #15

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.3862. Min Act: -0.0000

Data Index: 255220 (The Pile)

Max Activating Token Index: 471

Text #16

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.3729. Min Act: -0.0000

Data Index: 1781006 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.2525. Min Act: -0.0000

Data Index: 1812466 (The Pile)

Max Activating Token Index: 415

Text #18

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.2524. Min Act: -0.0000

Data Index: 462247 (The Pile)

Max Activating Token Index: 981

Text #19

Max Range: 1.8030. Min Range: -1.8030

Max Act: 1.3592. Min Act: -0.0000

Data Index: 1841863 (The Pile)

Max Activating Token Index: 230