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

Dataset: The Pile

Neuron 1222 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.5635. Min Act: -0.0000

Data Index: 801446 (The Pile)

Max Activating Token Index: 168

Text #1

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.5942. Min Act: -0.0000

Data Index: 1628451 (The Pile)

Max Activating Token Index: 651

Text #2

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4858. Min Act: -0.0000

Data Index: 1118249 (The Pile)

Max Activating Token Index: 879

Text #3

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.5490. Min Act: -0.0000

Data Index: 46367 (The Pile)

Max Activating Token Index: 116

Text #4

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1643606 (The Pile)

Max Activating Token Index: 595

Text #5

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1908608 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1089487 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.5300. Min Act: -0.0000

Data Index: 1701817 (The Pile)

Max Activating Token Index: 273

Text #8

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.5092. Min Act: -0.0000

Data Index: 962792 (The Pile)

Max Activating Token Index: 86

Text #9

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4194. Min Act: -0.0000

Data Index: 1574019 (The Pile)

Max Activating Token Index: 937

Text #10

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1110932 (The Pile)

Max Activating Token Index: 626

Text #11

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4818. Min Act: 0.0001

Data Index: 214662 (The Pile)

Max Activating Token Index: 982

Text #12

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4542. Min Act: -0.0000

Data Index: 585495 (The Pile)

Max Activating Token Index: 97

Text #13

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1124808 (The Pile)

Max Activating Token Index: 39

Text #14

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1730449 (The Pile)

Max Activating Token Index: 55

Text #15

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.5059. Min Act: -0.0000

Data Index: 1120559 (The Pile)

Max Activating Token Index: 32

Text #16

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4993. Min Act: -0.0000

Data Index: 813800 (The Pile)

Max Activating Token Index: 906

Text #17

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1035160 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4552. Min Act: 0.0001

Data Index: 1342436 (The Pile)

Max Activating Token Index: 808

Text #19

Max Range: 0.6002. Min Range: -0.6002

Max Act: 0.4842. Min Act: -0.0000

Data Index: 323654 (The Pile)

Max Activating Token Index: 80