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

Dataset: The Pile

Neuron 54 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: 1.7240. Min Range: -1.7240

Max Act: 1.7240. Min Act: -0.0000

Data Index: 1191190 (The Pile)

Max Activating Token Index: 8

Text #1

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.3032. Min Act: -0.0000

Data Index: 1996765 (The Pile)

Max Activating Token Index: 7

Text #2

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.3355. Min Act: -0.0000

Data Index: 626319 (The Pile)

Max Activating Token Index: 9

Text #3

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.2940. Min Act: -0.0000

Data Index: 1115904 (The Pile)

Max Activating Token Index: 6

Text #4

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.2404. Min Act: -0.0000

Data Index: 940729 (The Pile)

Max Activating Token Index: 17

Text #5

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1696. Min Act: -0.0000

Data Index: 913049 (The Pile)

Max Activating Token Index: 73

Text #6

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.2563. Min Act: -0.0000

Data Index: 146466 (The Pile)

Max Activating Token Index: 445

Text #7

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.2313. Min Act: -0.0000

Data Index: 1084063 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1751. Min Act: -0.0000

Data Index: 1359769 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1201. Min Act: -0.0000

Data Index: 495045 (The Pile)

Max Activating Token Index: 251

Text #10

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1223. Min Act: -0.0000

Data Index: 376046 (The Pile)

Max Activating Token Index: 952

Text #11

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1571. Min Act: -0.0000

Data Index: 1624941 (The Pile)

Max Activating Token Index: 14

Text #12

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.0646. Min Act: -0.0000

Data Index: 468570 (The Pile)

Max Activating Token Index: 51

Text #13

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1332. Min Act: -0.0000

Data Index: 752061 (The Pile)

Max Activating Token Index: 775

Text #14

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.2549. Min Act: -0.0000

Data Index: 433385 (The Pile)

Max Activating Token Index: 583

Text #15

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.1005. Min Act: -0.0000

Data Index: 877601 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.0333. Min Act: -0.0000

Data Index: 772146 (The Pile)

Max Activating Token Index: 6

Text #17

Max Range: 1.7240. Min Range: -1.7240

Max Act: 0.8373. Min Act: -0.0000

Data Index: 1494003 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.0914. Min Act: -0.0000

Data Index: 37088 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 1.7240. Min Range: -1.7240

Max Act: 1.0202. Min Act: -0.0000

Data Index: 954944 (The Pile)

Max Activating Token Index: 16