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

Dataset: The Pile

Neuron 4321 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: 0.1187. Min Range: -0.1187

Max Act: 0.1165. Min Act: -0.0000

Data Index: 107323 (The Pile)

Max Activating Token Index: 829

Text #1

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1187. Min Act: -0.0000

Data Index: 562042 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1114. Min Act: -0.0000

Data Index: 533701 (The Pile)

Max Activating Token Index: 637

Text #3

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1189077 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1118. Min Act: -0.0000

Data Index: 163076 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1974641 (The Pile)

Max Activating Token Index: 205

Text #6

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0986. Min Act: -0.0000

Data Index: 673153 (The Pile)

Max Activating Token Index: 321

Text #7

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1098. Min Act: -0.0000

Data Index: 1062962 (The Pile)

Max Activating Token Index: 388

Text #8

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1253987 (The Pile)

Max Activating Token Index: 310

Text #9

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1820471 (The Pile)

Max Activating Token Index: 550

Text #10

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1040. Min Act: -0.0000

Data Index: 720944 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0934. Min Act: -0.0000

Data Index: 651000 (The Pile)

Max Activating Token Index: 903

Text #12

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1005. Min Act: -0.0000

Data Index: 848151 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1020. Min Act: -0.0000

Data Index: 885857 (The Pile)

Max Activating Token Index: 641

Text #14

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1025. Min Act: -0.0000

Data Index: 35823 (The Pile)

Max Activating Token Index: 93

Text #15

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1764579 (The Pile)

Max Activating Token Index: 482

Text #16

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0990. Min Act: -0.0000

Data Index: 552636 (The Pile)

Max Activating Token Index: 353

Text #17

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1784406 (The Pile)

Max Activating Token Index: 629

Text #18

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.0984. Min Act: -0.0000

Data Index: 301374 (The Pile)

Max Activating Token Index: 716

Text #19

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1086097 (The Pile)

Max Activating Token Index: 64