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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4185 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1351. Min Act: -0.0001

Data Index: 708961 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1371. Min Act: -0.0000

Data Index: 751452 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1042096 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1181. Min Act: -0.0000

Data Index: 62724 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1068. Min Act: -0.0000

Data Index: 709395 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1138. Min Act: -0.0000

Data Index: 600253 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1085. Min Act: -0.0000

Data Index: 172860 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1070. Min Act: -0.0000

Data Index: 151493 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1007. Min Act: -0.0000

Data Index: 865465 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1045. Min Act: -0.0000

Data Index: 148959 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1013. Min Act: -0.0000

Data Index: 243976 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0991. Min Act: -0.0000

Data Index: 982729 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1293214 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1042. Min Act: -0.0000

Data Index: 163574 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1010. Min Act: -0.0000

Data Index: 4528 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1047. Min Act: -0.0000

Data Index: 431644 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0965. Min Act: -0.0001

Data Index: 522623 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1342311 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1310048 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0918. Min Act: -0.0000

Data Index: 918849 (C4 (Web Text))

Max Activating Token Index: 271