Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2700 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.5260. Min Act: -0.0001

Data Index: 44208 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.4081. Min Act: -0.0000

Data Index: 983781 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.2542. Min Act: -0.0001

Data Index: 671611 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.2365. Min Act: -0.0000

Data Index: 857078 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.2331. Min Act: -0.0000

Data Index: 169530 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.3044. Min Act: -0.0000

Data Index: 569696 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.2643. Min Act: -0.0000

Data Index: 627171 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.2109. Min Act: -0.0000

Data Index: 169125 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.2853. Min Act: -0.0000

Data Index: 884084 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.2057. Min Act: -0.0000

Data Index: 3630 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.1498. Min Act: -0.0000

Data Index: 6982 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.1577. Min Act: -0.0000

Data Index: 102850 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.1150. Min Act: -0.0001

Data Index: 888703 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.1065. Min Act: -0.0000

Data Index: 876201 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.1006. Min Act: -0.0000

Data Index: 59975 (C4 (Web Text))

Max Activating Token Index: 917

Text #15

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.0973. Min Act: -0.0001

Data Index: 1312467 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.1261. Min Act: -0.0001

Data Index: 1153351 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.0257. Min Act: -0.0000

Data Index: 896564 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.1123. Min Act: -0.0001

Data Index: 71591 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 1.5260. Min Range: -1.5260

Max Act: 1.0769. Min Act: -0.0000

Data Index: 700549 (C4 (Web Text))

Max Activating Token Index: 340