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

Dataset: The Pile

Neuron 3011 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0400. Min Range: -1.0400

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1994667 (The Pile)

Max Activating Token Index: 991

Text #1

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.9940. Min Act: -0.0000

Data Index: 642681 (The Pile)

Max Activating Token Index: 1008

Text #2

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8282. Min Act: -0.0000

Data Index: 543024 (The Pile)

Max Activating Token Index: 353

Text #3

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1659097 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7934. Min Act: -0.0000

Data Index: 787753 (The Pile)

Max Activating Token Index: 528

Text #5

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8028. Min Act: -0.0000

Data Index: 47833 (The Pile)

Max Activating Token Index: 849

Text #6

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1035869 (The Pile)

Max Activating Token Index: 309

Text #7

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7896. Min Act: -0.0000

Data Index: 374097 (The Pile)

Max Activating Token Index: 454

Text #8

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.8079. Min Act: -0.0000

Data Index: 688581 (The Pile)

Max Activating Token Index: 644

Text #9

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1234875 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.6917. Min Act: -0.0000

Data Index: 123182 (The Pile)

Max Activating Token Index: 785

Text #11

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7404. Min Act: -0.0000

Data Index: 75087 (The Pile)

Max Activating Token Index: 392

Text #12

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7593. Min Act: -0.0000

Data Index: 602370 (The Pile)

Max Activating Token Index: 912

Text #13

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7406. Min Act: -0.0000

Data Index: 1413323 (The Pile)

Max Activating Token Index: 570

Text #14

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1698106 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7022. Min Act: -0.0000

Data Index: 186441 (The Pile)

Max Activating Token Index: 619

Text #16

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1507892 (The Pile)

Max Activating Token Index: 572

Text #17

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7302. Min Act: -0.0000

Data Index: 543738 (The Pile)

Max Activating Token Index: 586

Text #18

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7129. Min Act: -0.0000

Data Index: 842966 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 1.0400. Min Range: -1.0400

Max Act: 0.7072. Min Act: -0.0000

Data Index: 192600 (The Pile)

Max Activating Token Index: 465