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

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

Neuron 1962 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: 1.6911. Min Range: -1.6911

Max Act: 1.2856. Min Act: -0.0001

Data Index: 1232138 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.6911. Min Act: -0.0001

Data Index: 770244 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3664. Min Act: -0.0001

Data Index: 839975 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.5077. Min Act: -0.0001

Data Index: 892213 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.3339. Min Act: -0.0001

Data Index: 1132583 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.5726. Min Act: -0.0001

Data Index: 1224488 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.2050. Min Act: -0.0001

Data Index: 1261784 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.0514. Min Act: -0.0001

Data Index: 975000 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.0601. Min Act: -0.0001

Data Index: 111979 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 1.6911. Min Range: -1.6911

Max Act: 0.9262. Min Act: -0.0001

Data Index: 303640 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.1536. Min Act: -0.0001

Data Index: 931439 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.0503. Min Act: -0.0001

Data Index: 1117029 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.0938. Min Act: -0.0001

Data Index: 193498 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.0923. Min Act: -0.0001

Data Index: 20019 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 1.6911. Min Range: -1.6911

Max Act: 1.0615. Min Act: -0.0001

Data Index: 547649 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 1.6911. Min Range: -1.6911

Max Act: 0.9519. Min Act: -0.0001

Data Index: 199564 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 1.6911. Min Range: -1.6911

Max Act: 0.9508. Min Act: -0.0001

Data Index: 142891 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 1.6911. Min Range: -1.6911

Max Act: 0.8883. Min Act: -0.0001

Data Index: 563657 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 1.6911. Min Range: -1.6911

Max Act: 0.9511. Min Act: -0.0001

Data Index: 515045 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 1.6911. Min Range: -1.6911

Max Act: 0.8943. Min Act: -0.0001

Data Index: 1156085 (C4 (Web Text))

Max Activating Token Index: 681