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

Dataset: The Pile

Neuron 558 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1471484 (The Pile)

Max Activating Token Index: 444

Text #1

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1780432 (The Pile)

Max Activating Token Index: 304

Text #2

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.5201. Min Act: -0.0000

Data Index: 115170 (The Pile)

Max Activating Token Index: 363

Text #3

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.5192. Min Act: -0.0000

Data Index: 119500 (The Pile)

Max Activating Token Index: 28

Text #4

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4941. Min Act: -0.0000

Data Index: 630881 (The Pile)

Max Activating Token Index: 131

Text #5

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1658195 (The Pile)

Max Activating Token Index: 125

Text #6

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4796. Min Act: -0.0000

Data Index: 748162 (The Pile)

Max Activating Token Index: 13

Text #7

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4630. Min Act: -0.0000

Data Index: 1050446 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4460. Min Act: -0.0000

Data Index: 1317491 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4565. Min Act: -0.0000

Data Index: 1629737 (The Pile)

Max Activating Token Index: 80

Text #10

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4693. Min Act: -0.0000

Data Index: 1227597 (The Pile)

Max Activating Token Index: 71

Text #11

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1084483 (The Pile)

Max Activating Token Index: 65

Text #12

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4301. Min Act: -0.0000

Data Index: 1397665 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1192369 (The Pile)

Max Activating Token Index: 211

Text #14

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1454342 (The Pile)

Max Activating Token Index: 28

Text #15

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4645. Min Act: -0.0000

Data Index: 292600 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1769813 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1192596 (The Pile)

Max Activating Token Index: 15

Text #18

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4366. Min Act: -0.0000

Data Index: 868560 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1055058 (The Pile)

Max Activating Token Index: 454