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

Dataset: The Pile

Neuron 3960 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1203. Min Act: 0.0000

Data Index: 990477 (The Pile)

Max Activating Token Index: 459

Text #1

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1241. Min Act: -0.0000

Data Index: 967995 (The Pile)

Max Activating Token Index: 856

Text #2

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1328628 (The Pile)

Max Activating Token Index: 527

Text #3

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1885600 (The Pile)

Max Activating Token Index: 471

Text #4

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1539129 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1511722 (The Pile)

Max Activating Token Index: 847

Text #6

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1694949 (The Pile)

Max Activating Token Index: 425

Text #7

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1123. Min Act: -0.0000

Data Index: 771152 (The Pile)

Max Activating Token Index: 722

Text #8

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1375218 (The Pile)

Max Activating Token Index: 696

Text #9

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1032. Min Act: -0.0000

Data Index: 599910 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1011. Min Act: -0.0000

Data Index: 352905 (The Pile)

Max Activating Token Index: 727

Text #11

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1051. Min Act: -0.0000

Data Index: 544500 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1682521 (The Pile)

Max Activating Token Index: 353

Text #13

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1920297 (The Pile)

Max Activating Token Index: 910

Text #14

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1766149 (The Pile)

Max Activating Token Index: 794

Text #15

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1387864 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1022. Min Act: -0.0000

Data Index: 1117749 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1013. Min Act: -0.0000

Data Index: 411277 (The Pile)

Max Activating Token Index: 323

Text #18

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.1040. Min Act: -0.0000

Data Index: 1996640 (The Pile)

Max Activating Token Index: 369

Text #19

Max Range: 0.1241. Min Range: -0.1241

Max Act: 0.0860. Min Act: -0.0000

Data Index: 221788 (The Pile)

Max Activating Token Index: 602