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

Dataset: The Pile

Neuron 2441 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: 1.1210. Min Range: -1.1210

Max Act: 1.1210. Min Act: -0.0000

Data Index: 865073 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 1.1210. Min Range: -1.1210

Max Act: 1.0133. Min Act: -0.0000

Data Index: 1340574 (The Pile)

Max Activating Token Index: 475

Text #2

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9969. Min Act: -0.0000

Data Index: 1409223 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 1.1210. Min Range: -1.1210

Max Act: 1.0809. Min Act: -0.0000

Data Index: 1064395 (The Pile)

Max Activating Token Index: 992

Text #4

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9525. Min Act: -0.0000

Data Index: 602530 (The Pile)

Max Activating Token Index: 352

Text #5

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9436. Min Act: -0.0000

Data Index: 97844 (The Pile)

Max Activating Token Index: 734

Text #6

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.9159. Min Act: -0.0000

Data Index: 1888842 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1983708 (The Pile)

Max Activating Token Index: 259

Text #8

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8589. Min Act: -0.0000

Data Index: 297202 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8583. Min Act: -0.0000

Data Index: 499904 (The Pile)

Max Activating Token Index: 48

Text #10

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1939275 (The Pile)

Max Activating Token Index: 95

Text #11

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8198. Min Act: -0.0000

Data Index: 506130 (The Pile)

Max Activating Token Index: 421

Text #12

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1451157 (The Pile)

Max Activating Token Index: 13

Text #13

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7616. Min Act: -0.0000

Data Index: 976773 (The Pile)

Max Activating Token Index: 259

Text #14

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7145. Min Act: -0.0000

Data Index: 6965 (The Pile)

Max Activating Token Index: 702

Text #15

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.6641. Min Act: -0.0000

Data Index: 320991 (The Pile)

Max Activating Token Index: 926

Text #16

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.6837. Min Act: -0.0000

Data Index: 206067 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1001257 (The Pile)

Max Activating Token Index: 875

Text #18

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7107. Min Act: -0.0000

Data Index: 118981 (The Pile)

Max Activating Token Index: 986

Text #19

Max Range: 1.1210. Min Range: -1.1210

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1506063 (The Pile)

Max Activating Token Index: 579