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

Dataset: The Pile

Neuron 3795 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: 1.1032. Min Range: -1.1032

Max Act: 1.1032. Min Act: -0.0000

Data Index: 177946 (The Pile)

Max Activating Token Index: 542

Text #1

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.9243. Min Act: -0.0000

Data Index: 460347 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.8149. Min Act: -0.0000

Data Index: 216592 (The Pile)

Max Activating Token Index: 966

Text #3

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1769759 (The Pile)

Max Activating Token Index: 466

Text #4

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1414352 (The Pile)

Max Activating Token Index: 946

Text #5

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1414398 (The Pile)

Max Activating Token Index: 388

Text #6

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1463800 (The Pile)

Max Activating Token Index: 726

Text #7

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7555. Min Act: -0.0000

Data Index: 895952 (The Pile)

Max Activating Token Index: 863

Text #8

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1631172 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1237666 (The Pile)

Max Activating Token Index: 830

Text #10

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7374. Min Act: -0.0000

Data Index: 676385 (The Pile)

Max Activating Token Index: 26

Text #11

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7096. Min Act: -0.0000

Data Index: 798786 (The Pile)

Max Activating Token Index: 827

Text #12

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7025. Min Act: -0.0000

Data Index: 710280 (The Pile)

Max Activating Token Index: 408

Text #13

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7305. Min Act: -0.0000

Data Index: 330440 (The Pile)

Max Activating Token Index: 685

Text #14

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7119. Min Act: -0.0000

Data Index: 1244502 (The Pile)

Max Activating Token Index: 712

Text #15

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1742737 (The Pile)

Max Activating Token Index: 775

Text #16

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.6886. Min Act: -0.0000

Data Index: 971568 (The Pile)

Max Activating Token Index: 575

Text #17

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1420103 (The Pile)

Max Activating Token Index: 598

Text #18

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.6544. Min Act: -0.0000

Data Index: 757689 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 1.1032. Min Range: -1.1032

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1925857 (The Pile)

Max Activating Token Index: 798