Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2902 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.2317. Min Act: 0.0000

Data Index: 456881 (The Pile)

Max Activating Token Index: 83

Text #1

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1234180 (The Pile)

Max Activating Token Index: 263

Text #2

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.2131. Min Act: -0.0000

Data Index: 1189236 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1881. Min Act: -0.0000

Data Index: 221156 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1982. Min Act: -0.0000

Data Index: 88569 (The Pile)

Max Activating Token Index: 829

Text #5

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1060843 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1955. Min Act: -0.0000

Data Index: 276786 (The Pile)

Max Activating Token Index: 319

Text #7

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1002780 (The Pile)

Max Activating Token Index: 893

Text #8

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1374935 (The Pile)

Max Activating Token Index: 993

Text #9

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1869982 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1934. Min Act: -0.0000

Data Index: 1166750 (The Pile)

Max Activating Token Index: 725

Text #11

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1808. Min Act: -0.0000

Data Index: 421932 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1849. Min Act: -0.0000

Data Index: 821754 (The Pile)

Max Activating Token Index: 74

Text #13

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1994552 (The Pile)

Max Activating Token Index: 520

Text #14

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1838. Min Act: -0.0000

Data Index: 218741 (The Pile)

Max Activating Token Index: 547

Text #15

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1734155 (The Pile)

Max Activating Token Index: 621

Text #16

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1879. Min Act: -0.0000

Data Index: 920447 (The Pile)

Max Activating Token Index: 87

Text #17

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1337330 (The Pile)

Max Activating Token Index: 78

Text #18

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1796. Min Act: -0.0000

Data Index: 73605 (The Pile)

Max Activating Token Index: 440

Text #19

Max Range: 0.2317. Min Range: -0.2317

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1589301 (The Pile)

Max Activating Token Index: 553