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

Dataset: The Pile

Neuron 4765 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.2777. Min Act: -0.0000

Data Index: 1376239 (The Pile)

Max Activating Token Index: 356

Text #1

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.1194. Min Act: -0.0000

Data Index: 1736180 (The Pile)

Max Activating Token Index: 286

Text #2

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.1509. Min Act: -0.0000

Data Index: 733060 (The Pile)

Max Activating Token Index: 156

Text #3

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.1153. Min Act: -0.0000

Data Index: 1918799 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0064. Min Act: -0.0000

Data Index: 1203577 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0889. Min Act: -0.0000

Data Index: 388983 (The Pile)

Max Activating Token Index: 776

Text #6

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.1578. Min Act: -0.0001

Data Index: 505157 (The Pile)

Max Activating Token Index: 245

Text #7

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0506. Min Act: -0.0000

Data Index: 1875123 (The Pile)

Max Activating Token Index: 179

Text #8

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0034. Min Act: -0.0000

Data Index: 1190335 (The Pile)

Max Activating Token Index: 74

Text #9

Max Range: 1.2777. Min Range: -1.2777

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1309183 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1290688 (The Pile)

Max Activating Token Index: 827

Text #11

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0476. Min Act: -0.0000

Data Index: 1600112 (The Pile)

Max Activating Token Index: 86

Text #12

Max Range: 1.2777. Min Range: -1.2777

Max Act: 0.8403. Min Act: -0.0000

Data Index: 798404 (The Pile)

Max Activating Token Index: 799

Text #13

Max Range: 1.2777. Min Range: -1.2777

Max Act: 0.9916. Min Act: -0.0000

Data Index: 406303 (The Pile)

Max Activating Token Index: 45

Text #14

Max Range: 1.2777. Min Range: -1.2777

Max Act: 0.8807. Min Act: -0.0000

Data Index: 946402 (The Pile)

Max Activating Token Index: 1010

Text #15

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0192. Min Act: -0.0000

Data Index: 975233 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 1.2777. Min Range: -1.2777

Max Act: 0.9405. Min Act: -0.0000

Data Index: 1152282 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 1.2777. Min Range: -1.2777

Max Act: 0.8630. Min Act: -0.0000

Data Index: 437335 (The Pile)

Max Activating Token Index: 756

Text #18

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0253. Min Act: -0.0000

Data Index: 659322 (The Pile)

Max Activating Token Index: 819

Text #19

Max Range: 1.2777. Min Range: -1.2777

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1577480 (The Pile)

Max Activating Token Index: 227