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

Dataset: The Pile

Neuron 3858 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: 0.1430. Min Range: -0.1430

Max Act: 0.1430. Min Act: -0.0000

Data Index: 1248764 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1607743 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1028448 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1281. Min Act: -0.0000

Data Index: 849680 (The Pile)

Max Activating Token Index: 711

Text #4

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1191. Min Act: -0.0000

Data Index: 362420 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1226. Min Act: -0.0000

Data Index: 711919 (The Pile)

Max Activating Token Index: 298

Text #6

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1111. Min Act: -0.0000

Data Index: 720365 (The Pile)

Max Activating Token Index: 594

Text #7

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1107. Min Act: -0.0000

Data Index: 1129273 (The Pile)

Max Activating Token Index: 34

Text #8

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1105. Min Act: -0.0000

Data Index: 1298735 (The Pile)

Max Activating Token Index: 636

Text #9

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1594107 (The Pile)

Max Activating Token Index: 684

Text #10

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1136. Min Act: -0.0000

Data Index: 963320 (The Pile)

Max Activating Token Index: 275

Text #11

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1063. Min Act: -0.0000

Data Index: 750191 (The Pile)

Max Activating Token Index: 132

Text #12

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0996. Min Act: -0.0000

Data Index: 597589 (The Pile)

Max Activating Token Index: 752

Text #13

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1016. Min Act: -0.0000

Data Index: 1130242 (The Pile)

Max Activating Token Index: 198

Text #14

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1042. Min Act: -0.0000

Data Index: 245558 (The Pile)

Max Activating Token Index: 671

Text #15

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1046. Min Act: -0.0000

Data Index: 990743 (The Pile)

Max Activating Token Index: 893

Text #16

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1039. Min Act: -0.0000

Data Index: 113528 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0992. Min Act: -0.0000

Data Index: 1255127 (The Pile)

Max Activating Token Index: 504

Text #18

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1387580 (The Pile)

Max Activating Token Index: 735

Text #19

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1013587 (The Pile)

Max Activating Token Index: 51