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

Dataset: The Pile

Neuron 1098 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: 0.1146. Min Range: -0.1146

Max Act: 0.1146. Min Act: -0.0000

Data Index: 784758 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0973. Min Act: -0.0000

Data Index: 18387 (The Pile)

Max Activating Token Index: 148

Text #2

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0988. Min Act: -0.0000

Data Index: 578829 (The Pile)

Max Activating Token Index: 947

Text #3

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1086. Min Act: -0.0000

Data Index: 234775 (The Pile)

Max Activating Token Index: 703

Text #4

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0994. Min Act: -0.0000

Data Index: 491581 (The Pile)

Max Activating Token Index: 883

Text #5

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1781984 (The Pile)

Max Activating Token Index: 659

Text #6

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0948. Min Act: -0.0000

Data Index: 499202 (The Pile)

Max Activating Token Index: 956

Text #7

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0975. Min Act: -0.0000

Data Index: 394586 (The Pile)

Max Activating Token Index: 345

Text #8

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1414851 (The Pile)

Max Activating Token Index: 759

Text #9

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0924. Min Act: -0.0000

Data Index: 102967 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0960. Min Act: -0.0000

Data Index: 176957 (The Pile)

Max Activating Token Index: 733

Text #11

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1692899 (The Pile)

Max Activating Token Index: 595

Text #12

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0949. Min Act: -0.0000

Data Index: 249919 (The Pile)

Max Activating Token Index: 655

Text #13

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1130474 (The Pile)

Max Activating Token Index: 849

Text #14

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1028545 (The Pile)

Max Activating Token Index: 464

Text #15

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1005. Min Act: -0.0000

Data Index: 128868 (The Pile)

Max Activating Token Index: 363

Text #16

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1567862 (The Pile)

Max Activating Token Index: 393

Text #17

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1842499 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1492943 (The Pile)

Max Activating Token Index: 459

Text #19

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0990. Min Act: -0.0000

Data Index: 885967 (The Pile)

Max Activating Token Index: 398