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

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

Neuron 3286 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: 0.1431. Min Range: -0.1431

Max Act: 0.1386. Min Act: -0.0000

Data Index: 548943 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1431. Min Act: -0.0000

Data Index: 486881 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1277. Min Act: -0.0000

Data Index: 822203 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1326. Min Act: -0.0000

Data Index: 16090 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1205. Min Act: -0.0000

Data Index: 310296 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1259. Min Act: -0.0000

Data Index: 1086969 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1246564 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1098. Min Act: -0.0000

Data Index: 1322524 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1083. Min Act: -0.0000

Data Index: 70088 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1080. Min Act: -0.0000

Data Index: 495059 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1035. Min Act: -0.0000

Data Index: 710479 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1115496 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1066. Min Act: -0.0000

Data Index: 431690 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.0969. Min Act: -0.0000

Data Index: 194155 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1027. Min Act: -0.0000

Data Index: 238881 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1054. Min Act: -0.0000

Data Index: 354859 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.1040. Min Act: -0.0000

Data Index: 601456 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.0943. Min Act: -0.0000

Data Index: 586914 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.0973. Min Act: -0.0000

Data Index: 1139683 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.1431. Min Range: -0.1431

Max Act: 0.0975. Min Act: -0.0000

Data Index: 318051 (C4 (Web Text))

Max Activating Token Index: 520