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

Dataset: The Pile

Neuron 673 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: 1.4393. Min Range: -1.4393

Max Act: 1.4393. Min Act: -0.0000

Data Index: 890299 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1307236 (The Pile)

Max Activating Token Index: 806

Text #2

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.9635. Min Act: -0.0000

Data Index: 17430 (The Pile)

Max Activating Token Index: 493

Text #3

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.9153. Min Act: -0.0000

Data Index: 179525 (The Pile)

Max Activating Token Index: 408

Text #4

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.9405. Min Act: -0.0000

Data Index: 478076 (The Pile)

Max Activating Token Index: 351

Text #5

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1398826 (The Pile)

Max Activating Token Index: 41

Text #6

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.8930. Min Act: -0.0000

Data Index: 788992 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.7943. Min Act: -0.0000

Data Index: 74190 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.8689. Min Act: -0.0000

Data Index: 1847624 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1820517 (The Pile)

Max Activating Token Index: 883

Text #10

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1724504 (The Pile)

Max Activating Token Index: 323

Text #11

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.7638. Min Act: -0.0000

Data Index: 553391 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1249885 (The Pile)

Max Activating Token Index: 82

Text #13

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.8445. Min Act: -0.0000

Data Index: 1925910 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.7364. Min Act: -0.0000

Data Index: 279765 (The Pile)

Max Activating Token Index: 966

Text #15

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.8342. Min Act: -0.0000

Data Index: 85688 (The Pile)

Max Activating Token Index: 835

Text #16

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.7559. Min Act: -0.0000

Data Index: 197221 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.7169. Min Act: -0.0000

Data Index: 992793 (The Pile)

Max Activating Token Index: 676

Text #18

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1370610 (The Pile)

Max Activating Token Index: 105

Text #19

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.7739. Min Act: -0.0000

Data Index: 1172925 (The Pile)

Max Activating Token Index: 41