Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1847 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.6208. Min Act: -0.0000

Data Index: 272121 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.4367. Min Act: -0.0000

Data Index: 784397 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.5105. Min Act: -0.0000

Data Index: 1193065 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1277904 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.3489. Min Act: -0.0000

Data Index: 1288266 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.2585. Min Act: -0.0000

Data Index: 374437 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.2673. Min Act: -0.0000

Data Index: 985395 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.0867. Min Act: -0.0000

Data Index: 1065821 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.2395. Min Act: -0.0000

Data Index: 477764 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.1583. Min Act: -0.0000

Data Index: 626598 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.2078. Min Act: -0.0000

Data Index: 1137120 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.2005. Min Act: -0.0000

Data Index: 284415 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.1247. Min Act: -0.0000

Data Index: 364142 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.2411. Min Act: -0.0000

Data Index: 194986 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.2570. Min Act: -0.0000

Data Index: 241000 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.1824. Min Act: -0.0000

Data Index: 1296405 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.0512. Min Act: -0.0000

Data Index: 981593 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.1449. Min Act: -0.0000

Data Index: 803544 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.1634. Min Act: -0.0000

Data Index: 133258 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 1.6208. Min Range: -1.6208

Max Act: 1.1781. Min Act: -0.0000

Data Index: 377653 (C4 (Web Text))

Max Activating Token Index: 216