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

Dataset: The Pile

Neuron 383 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.7740. Min Act: -0.0000

Data Index: 1628156 (The Pile)

Max Activating Token Index: 456

Text #1

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.3076. Min Act: -0.0000

Data Index: 682002 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.1704. Min Act: -0.0000

Data Index: 839460 (The Pile)

Max Activating Token Index: 566

Text #3

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.1014. Min Act: -0.0000

Data Index: 148024 (The Pile)

Max Activating Token Index: 702

Text #4

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.0090. Min Act: -0.0000

Data Index: 464242 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 1.7740. Min Range: -1.7740

Max Act: 0.9405. Min Act: -0.0000

Data Index: 1624457 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 1.7740. Min Range: -1.7740

Max Act: 0.9747. Min Act: -0.0000

Data Index: 380321 (The Pile)

Max Activating Token Index: 950

Text #7

Max Range: 1.7740. Min Range: -1.7740

Max Act: 0.9030. Min Act: -0.0000

Data Index: 1945912 (The Pile)

Max Activating Token Index: 240

Text #8

Max Range: 1.7740. Min Range: -1.7740

Max Act: 1.0106. Min Act: -0.0000

Data Index: 1656935 (The Pile)

Max Activating Token Index: 740

Text #9

Max Range: 1.7740. Min Range: -1.7740

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1290130 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 1.7740. Min Range: -1.7740

Max Act: 0.8945. Min Act: -0.0000

Data Index: 519648 (The Pile)

Max Activating Token Index: 1013

Text #11

Max Range: 1.7740. Min Range: -1.7740

Max Act: 0.8853. Min Act: -0.0000

Data Index: 1499163 (The Pile)

Max Activating Token Index: 316

Text #12

Max Range: 1.7740. Min Range: -1.7740

Max Act: 0.8901. Min Act: -0.0000

Data Index: 257276 (The Pile)

Max Activating Token Index: 105

Text #13

Max Range: 1.7740. Min Range: -1.7740

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1985951 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 1.7740. Min Range: -1.7740

Max Act: 0.8274. Min Act: -0.0000

Data Index: 728492 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 1.7740. Min Range: -1.7740

Max Act: 0.8349. Min Act: -0.0000

Data Index: 207540 (The Pile)

Max Activating Token Index: 444

Text #16

Max Range: 1.7740. Min Range: -1.7740

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1199999 (The Pile)

Max Activating Token Index: 514

Text #17

Max Range: 1.7740. Min Range: -1.7740

Max Act: 0.8484. Min Act: -0.0000

Data Index: 890627 (The Pile)

Max Activating Token Index: 672

Text #18

Max Range: 1.7740. Min Range: -1.7740

Max Act: 0.8345. Min Act: -0.0000

Data Index: 1513013 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 1.7740. Min Range: -1.7740

Max Act: 0.8805. Min Act: -0.0000

Data Index: 186342 (The Pile)

Max Activating Token Index: 640