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

Dataset: The Pile

Neuron 3602 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9170. Min Range: -1.9170

Max Act: 0.8223. Min Act: -0.0000

Data Index: 1494091 (The Pile)

Max Activating Token Index: 682

Text #1

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.7780. Min Act: -0.0000

Data Index: 793305 (The Pile)

Max Activating Token Index: 490

Text #2

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.7139. Min Act: -0.0000

Data Index: 868723 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.8410. Min Act: -0.0000

Data Index: 174044 (The Pile)

Max Activating Token Index: 34

Text #4

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.6433. Min Act: -0.0000

Data Index: 1915918 (The Pile)

Max Activating Token Index: 22

Text #5

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.9170. Min Act: -0.0000

Data Index: 807771 (The Pile)

Max Activating Token Index: 683

Text #6

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.3756. Min Act: -0.0000

Data Index: 1899429 (The Pile)

Max Activating Token Index: 328

Text #7

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.4857. Min Act: -0.0000

Data Index: 349168 (The Pile)

Max Activating Token Index: 156

Text #8

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.7613. Min Act: -0.0000

Data Index: 1124496 (The Pile)

Max Activating Token Index: 232

Text #9

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.3496. Min Act: -0.0000

Data Index: 924887 (The Pile)

Max Activating Token Index: 35

Text #10

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.4466. Min Act: -0.0000

Data Index: 364460 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.4094. Min Act: -0.0000

Data Index: 540714 (The Pile)

Max Activating Token Index: 25

Text #12

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.2944. Min Act: -0.0000

Data Index: 1120079 (The Pile)

Max Activating Token Index: 198

Text #13

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.3818. Min Act: -0.0000

Data Index: 432400 (The Pile)

Max Activating Token Index: 975

Text #14

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.4371. Min Act: -0.0000

Data Index: 188197 (The Pile)

Max Activating Token Index: 192

Text #15

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.4288. Min Act: -0.0000

Data Index: 1950917 (The Pile)

Max Activating Token Index: 885

Text #16

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.3309. Min Act: -0.0000

Data Index: 1384610 (The Pile)

Max Activating Token Index: 169

Text #17

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.2987. Min Act: -0.0000

Data Index: 1436998 (The Pile)

Max Activating Token Index: 524

Text #18

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.3880. Min Act: -0.0000

Data Index: 882596 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 1.9170. Min Range: -1.9170

Max Act: 1.3580. Min Act: -0.0000

Data Index: 37992 (The Pile)

Max Activating Token Index: 912