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

Dataset: The Pile

Neuron 3394 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: 0.1151. Min Range: -0.1151

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1586964 (The Pile)

Max Activating Token Index: 531

Text #1

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1065. Min Act: -0.0000

Data Index: 1698253 (The Pile)

Max Activating Token Index: 853

Text #2

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1048. Min Act: -0.0000

Data Index: 924560 (The Pile)

Max Activating Token Index: 997

Text #3

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1814950 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1011. Min Act: -0.0000

Data Index: 481678 (The Pile)

Max Activating Token Index: 648

Text #5

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1101. Min Act: -0.0000

Data Index: 695212 (The Pile)

Max Activating Token Index: 965

Text #6

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0973. Min Act: -0.0000

Data Index: 740544 (The Pile)

Max Activating Token Index: 585

Text #7

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1363458 (The Pile)

Max Activating Token Index: 1010

Text #8

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1254582 (The Pile)

Max Activating Token Index: 805

Text #9

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1510951 (The Pile)

Max Activating Token Index: 937

Text #10

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0873. Min Act: -0.0000

Data Index: 1606789 (The Pile)

Max Activating Token Index: 796

Text #11

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0881. Min Act: -0.0000

Data Index: 1402772 (The Pile)

Max Activating Token Index: 814

Text #12

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1624478 (The Pile)

Max Activating Token Index: 655

Text #13

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1538671 (The Pile)

Max Activating Token Index: 659

Text #14

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.1005. Min Act: -0.0000

Data Index: 544616 (The Pile)

Max Activating Token Index: 898

Text #15

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0746. Min Act: -0.0000

Data Index: 453785 (The Pile)

Max Activating Token Index: 855

Text #16

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0957. Min Act: -0.0000

Data Index: 1284235 (The Pile)

Max Activating Token Index: 637

Text #17

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0826. Min Act: -0.0000

Data Index: 890152 (The Pile)

Max Activating Token Index: 433

Text #18

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0809. Min Act: -0.0000

Data Index: 325696 (The Pile)

Max Activating Token Index: 931

Text #19

Max Range: 0.1151. Min Range: -0.1151

Max Act: 0.0837. Min Act: -0.0000

Data Index: 363155 (The Pile)

Max Activating Token Index: 958