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

Dataset: The Pile

Neuron 3554 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: 0.5788. Min Range: -0.5788

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1853090 (The Pile)

Max Activating Token Index: 790

Text #1

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1205653 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.5078. Min Act: -0.0000

Data Index: 444201 (The Pile)

Max Activating Token Index: 905

Text #3

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1215273 (The Pile)

Max Activating Token Index: 218

Text #4

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4965. Min Act: -0.0000

Data Index: 86662 (The Pile)

Max Activating Token Index: 56

Text #5

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4404. Min Act: -0.0000

Data Index: 755002 (The Pile)

Max Activating Token Index: 43

Text #6

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4421. Min Act: -0.0000

Data Index: 214373 (The Pile)

Max Activating Token Index: 505

Text #7

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4024. Min Act: -0.0000

Data Index: 715472 (The Pile)

Max Activating Token Index: 131

Text #8

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4407. Min Act: -0.0000

Data Index: 762407 (The Pile)

Max Activating Token Index: 364

Text #9

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1125212 (The Pile)

Max Activating Token Index: 941

Text #10

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1261981 (The Pile)

Max Activating Token Index: 965

Text #11

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1545824 (The Pile)

Max Activating Token Index: 48

Text #12

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1542666 (The Pile)

Max Activating Token Index: 1022

Text #13

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1874813 (The Pile)

Max Activating Token Index: 131

Text #14

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3897. Min Act: -0.0000

Data Index: 299943 (The Pile)

Max Activating Token Index: 950

Text #15

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1147148 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4323. Min Act: -0.0000

Data Index: 103855 (The Pile)

Max Activating Token Index: 697

Text #17

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4094. Min Act: -0.0000

Data Index: 1865683 (The Pile)

Max Activating Token Index: 808

Text #18

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4033. Min Act: -0.0000

Data Index: 693646 (The Pile)

Max Activating Token Index: 976

Text #19

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4204. Min Act: -0.0000

Data Index: 1154118 (The Pile)

Max Activating Token Index: 1020