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

Dataset: The Pile

Neuron 2369 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.7200. Min Act: -0.0000

Data Index: 935632 (The Pile)

Max Activating Token Index: 566

Text #1

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.5640. Min Act: -0.0000

Data Index: 1313835 (The Pile)

Max Activating Token Index: 413

Text #2

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.3903. Min Act: -0.0000

Data Index: 49159 (The Pile)

Max Activating Token Index: 700

Text #3

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.3827. Min Act: -0.0000

Data Index: 973295 (The Pile)

Max Activating Token Index: 115

Text #4

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.3788. Min Act: -0.0000

Data Index: 375183 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.2366. Min Act: -0.0000

Data Index: 151918 (The Pile)

Max Activating Token Index: 548

Text #6

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.3141. Min Act: -0.0000

Data Index: 1760365 (The Pile)

Max Activating Token Index: 217

Text #7

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.2299. Min Act: -0.0000

Data Index: 1823755 (The Pile)

Max Activating Token Index: 621

Text #8

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.2285. Min Act: -0.0000

Data Index: 674429 (The Pile)

Max Activating Token Index: 339

Text #9

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.2398. Min Act: -0.0000

Data Index: 1484936 (The Pile)

Max Activating Token Index: 57

Text #10

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.2425. Min Act: -0.0000

Data Index: 693521 (The Pile)

Max Activating Token Index: 349

Text #11

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.2411. Min Act: -0.0000

Data Index: 1123705 (The Pile)

Max Activating Token Index: 153

Text #12

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.2721. Min Act: -0.0000

Data Index: 1429836 (The Pile)

Max Activating Token Index: 123

Text #13

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.1343. Min Act: -0.0000

Data Index: 1087870 (The Pile)

Max Activating Token Index: 62

Text #14

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.1353. Min Act: -0.0000

Data Index: 957225 (The Pile)

Max Activating Token Index: 508

Text #15

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.1856. Min Act: -0.0000

Data Index: 1001290 (The Pile)

Max Activating Token Index: 627

Text #16

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.1140. Min Act: -0.0000

Data Index: 641849 (The Pile)

Max Activating Token Index: 456

Text #17

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.1697. Min Act: -0.0000

Data Index: 608618 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.1904. Min Act: -0.0000

Data Index: 1662086 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 1.7200. Min Range: -1.7200

Max Act: 1.0832. Min Act: -0.0000

Data Index: 340917 (The Pile)

Max Activating Token Index: 675