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

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

Neuron 4050 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: 0.1473. Min Range: -0.1473

Max Act: 0.1473. Min Act: -0.0000

Data Index: 127699 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1327. Min Act: -0.0000

Data Index: 642805 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1343. Min Act: -0.0000

Data Index: 862364 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1125835 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1259. Min Act: -0.0000

Data Index: 13542 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1211. Min Act: -0.0000

Data Index: 557029 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1139. Min Act: -0.0000

Data Index: 792267 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1135. Min Act: -0.0000

Data Index: 486549 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1090077 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1117. Min Act: -0.0000

Data Index: 902365 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0933. Min Act: -0.0000

Data Index: 840229 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1060570 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1269533 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1087. Min Act: -0.0000

Data Index: 933038 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1086. Min Act: -0.0000

Data Index: 949957 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1002. Min Act: -0.0000

Data Index: 229766 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1174782 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1137904 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1069. Min Act: -0.0000

Data Index: 953549 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1068. Min Act: -0.0000

Data Index: 103756 (C4 (Web Text))

Max Activating Token Index: 471