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

Dataset: The Pile

Neuron 4190 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1547. Min Range: -7.1547

Max Act: 7.1547. Min Act: -0.0000

Data Index: 313210 (The Pile)

Max Activating Token Index: 17

Text #1

Max Range: 7.1547. Min Range: -7.1547

Max Act: 6.6590. Min Act: -0.0000

Data Index: 1503848 (The Pile)

Max Activating Token Index: 10

Text #2

Max Range: 7.1547. Min Range: -7.1547

Max Act: 6.3844. Min Act: -0.0000

Data Index: 1476185 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 7.1547. Min Range: -7.1547

Max Act: 6.2720. Min Act: -0.0000

Data Index: 511968 (The Pile)

Max Activating Token Index: 15

Text #4

Max Range: 7.1547. Min Range: -7.1547

Max Act: 5.9123. Min Act: -0.0000

Data Index: 1332913 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 7.1547. Min Range: -7.1547

Max Act: 5.8850. Min Act: -0.0000

Data Index: 624558 (The Pile)

Max Activating Token Index: 22

Text #6

Max Range: 7.1547. Min Range: -7.1547

Max Act: 5.7666. Min Act: -0.0000

Data Index: 400936 (The Pile)

Max Activating Token Index: 11

Text #7

Max Range: 7.1547. Min Range: -7.1547

Max Act: 6.1566. Min Act: -0.0000

Data Index: 961804 (The Pile)

Max Activating Token Index: 10

Text #8

Max Range: 7.1547. Min Range: -7.1547

Max Act: 5.8890. Min Act: -0.0000

Data Index: 1308590 (The Pile)

Max Activating Token Index: 11

Text #9

Max Range: 7.1547. Min Range: -7.1547

Max Act: 5.1141. Min Act: -0.0000

Data Index: 1609968 (The Pile)

Max Activating Token Index: 8

Text #10

Max Range: 7.1547. Min Range: -7.1547

Max Act: 5.1141. Min Act: -0.0000

Data Index: 384320 (The Pile)

Max Activating Token Index: 8

Text #11

Max Range: 7.1547. Min Range: -7.1547

Max Act: 5.2910. Min Act: -0.0000

Data Index: 559842 (The Pile)

Max Activating Token Index: 15

Text #12

Max Range: 7.1547. Min Range: -7.1547

Max Act: 5.5003. Min Act: -0.0000

Data Index: 1388394 (The Pile)

Max Activating Token Index: 7

Text #13

Max Range: 7.1547. Min Range: -7.1547

Max Act: 5.2636. Min Act: -0.0000

Data Index: 1001174 (The Pile)

Max Activating Token Index: 8

Text #14

Max Range: 7.1547. Min Range: -7.1547

Max Act: 5.2981. Min Act: -0.0000

Data Index: 415774 (The Pile)

Max Activating Token Index: 13

Text #15

Max Range: 7.1547. Min Range: -7.1547

Max Act: 5.1705. Min Act: -0.0000

Data Index: 1545593 (The Pile)

Max Activating Token Index: 11

Text #16

Max Range: 7.1547. Min Range: -7.1547

Max Act: 5.4191. Min Act: -0.0000

Data Index: 1995640 (The Pile)

Max Activating Token Index: 19

Text #17

Max Range: 7.1547. Min Range: -7.1547

Max Act: 5.4274. Min Act: -0.0000

Data Index: 1077968 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 7.1547. Min Range: -7.1547

Max Act: 5.1310. Min Act: -0.0000

Data Index: 1173821 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 7.1547. Min Range: -7.1547

Max Act: 5.1132. Min Act: -0.0000

Data Index: 252899 (The Pile)

Max Activating Token Index: 5