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

Dataset: The Pile

Neuron 2184 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.4000. Min Act: -0.0000

Data Index: 419803 (The Pile)

Max Activating Token Index: 455

Text #1

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.2740. Min Act: -0.0000

Data Index: 650144 (The Pile)

Max Activating Token Index: 974

Text #2

Max Range: 2.4000. Min Range: -2.4000

Max Act: 2.1238. Min Act: -0.0000

Data Index: 668826 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.9075. Min Act: -0.0000

Data Index: 1231227 (The Pile)

Max Activating Token Index: 16

Text #4

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.9375. Min Act: -0.0000

Data Index: 421259 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.9481. Min Act: -0.0000

Data Index: 1963235 (The Pile)

Max Activating Token Index: 24

Text #6

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.9208. Min Act: -0.0000

Data Index: 1571947 (The Pile)

Max Activating Token Index: 782

Text #7

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.7136. Min Act: -0.0000

Data Index: 1855250 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.9938. Min Act: -0.0000

Data Index: 1633034 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.6356. Min Act: -0.0000

Data Index: 100882 (The Pile)

Max Activating Token Index: 97

Text #10

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.7910. Min Act: -0.0000

Data Index: 1157122 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.6799. Min Act: -0.0000

Data Index: 468636 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.7068. Min Act: -0.0000

Data Index: 1137672 (The Pile)

Max Activating Token Index: 454

Text #13

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.8274. Min Act: -0.0000

Data Index: 468724 (The Pile)

Max Activating Token Index: 853

Text #14

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.8638. Min Act: -0.0000

Data Index: 1432296 (The Pile)

Max Activating Token Index: 501

Text #15

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.9410. Min Act: -0.0000

Data Index: 1626886 (The Pile)

Max Activating Token Index: 164

Text #16

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.7281. Min Act: -0.0000

Data Index: 17352 (The Pile)

Max Activating Token Index: 833

Text #17

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.7382. Min Act: -0.0000

Data Index: 1180078 (The Pile)

Max Activating Token Index: 267

Text #18

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.6771. Min Act: -0.0000

Data Index: 992102 (The Pile)

Max Activating Token Index: 833

Text #19

Max Range: 2.4000. Min Range: -2.4000

Max Act: 1.7700. Min Act: -0.0000

Data Index: 1629791 (The Pile)

Max Activating Token Index: 359