Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1075 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1835089 (The Pile)

Max Activating Token Index: 842

Text #1

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.7247. Min Act: -0.0000

Data Index: 169015 (The Pile)

Max Activating Token Index: 957

Text #2

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5871. Min Act: -0.0000

Data Index: 503298 (The Pile)

Max Activating Token Index: 789

Text #3

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1731671 (The Pile)

Max Activating Token Index: 498

Text #4

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5669. Min Act: -0.0000

Data Index: 763751 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5629. Min Act: -0.0000

Data Index: 1204727 (The Pile)

Max Activating Token Index: 573

Text #6

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1265057 (The Pile)

Max Activating Token Index: 65

Text #7

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4582. Min Act: -0.0000

Data Index: 291865 (The Pile)

Max Activating Token Index: 537

Text #8

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4714. Min Act: -0.0000

Data Index: 159823 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4655. Min Act: -0.0000

Data Index: 116714 (The Pile)

Max Activating Token Index: 115

Text #10

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1597423 (The Pile)

Max Activating Token Index: 930

Text #11

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1520079 (The Pile)

Max Activating Token Index: 832

Text #12

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4580. Min Act: -0.0000

Data Index: 809579 (The Pile)

Max Activating Token Index: 894

Text #13

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1839678 (The Pile)

Max Activating Token Index: 351

Text #14

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4043. Min Act: -0.0000

Data Index: 420252 (The Pile)

Max Activating Token Index: 718

Text #15

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4438. Min Act: -0.0000

Data Index: 119267 (The Pile)

Max Activating Token Index: 864

Text #16

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4710. Min Act: -0.0000

Data Index: 1216088 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4055. Min Act: -0.0000

Data Index: 473603 (The Pile)

Max Activating Token Index: 9

Text #18

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4173. Min Act: -0.0000

Data Index: 155376 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 0.7317. Min Range: -0.7317

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1076860 (The Pile)

Max Activating Token Index: 858