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

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

Neuron 1463 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1326. Min Act: -0.0001

Data Index: 542562 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1483132 (Python Code)

Max Activating Token Index: 367

Text #2

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1183. Min Act: -0.0001

Data Index: 961830 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1274. Min Act: -0.0001

Data Index: 1115086 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1149. Min Act: -0.0001

Data Index: 431930 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1078. Min Act: -0.0001

Data Index: 986583 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1349760 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0931. Min Act: -0.0001

Data Index: 890676 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1285. Min Act: -0.0001

Data Index: 4539 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1039. Min Act: -0.0001

Data Index: 622802 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1058. Min Act: -0.0001

Data Index: 626543 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1086. Min Act: -0.0001

Data Index: 618142 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1081. Min Act: -0.0001

Data Index: 783132 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0963. Min Act: -0.0001

Data Index: 453466 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1150423 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1005. Min Act: -0.0001

Data Index: 1089079 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1029. Min Act: -0.0001

Data Index: 1218443 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1068. Min Act: -0.0001

Data Index: 756591 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0996. Min Act: -0.0001

Data Index: 722478 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0946. Min Act: -0.0001

Data Index: 70393 (C4 (Web Text))

Max Activating Token Index: 640