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

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

Neuron 3151 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: 1.1903. Min Range: -1.1903

Max Act: 1.1903. Min Act: -0.0001

Data Index: 780735 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 1.1903. Min Range: -1.1903

Max Act: 1.0810. Min Act: -0.0001

Data Index: 966789 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.9611. Min Act: -0.0001

Data Index: 574256 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.9990. Min Act: -0.0001

Data Index: 624315 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.8942. Min Act: -0.0001

Data Index: 7569 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.8812. Min Act: -0.0001

Data Index: 782855 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.8950. Min Act: -0.0001

Data Index: 322375 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.9032. Min Act: -0.0001

Data Index: 570291 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.9223. Min Act: -0.0001

Data Index: 1316438 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.9014. Min Act: -0.0001

Data Index: 298039 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.8874. Min Act: -0.0001

Data Index: 863154 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.8735. Min Act: -0.0001

Data Index: 470854 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.8632. Min Act: -0.0001

Data Index: 694032 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.8091. Min Act: -0.0001

Data Index: 482756 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.8815. Min Act: -0.0001

Data Index: 173212 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.8762. Min Act: -0.0001

Data Index: 843988 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.8658. Min Act: -0.0001

Data Index: 163001 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.8236. Min Act: -0.0001

Data Index: 636486 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.7267. Min Act: -0.0001

Data Index: 261740 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 1.1903. Min Range: -1.1903

Max Act: 0.7526. Min Act: -0.0001

Data Index: 1355353 (C4 (Web Text))

Max Activating Token Index: 822