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

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

Neuron 1446 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1492. Min Range: -1.1492

Max Act: 1.1492. Min Act: -0.0000

Data Index: 769258 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.9883. Min Act: -0.0000

Data Index: 1073957 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.9799. Min Act: -0.0000

Data Index: 693684 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.9870. Min Act: 0.0000

Data Index: 1552856 (Python Code)

Max Activating Token Index: 251

Text #4

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1072510 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1388179 (Python Code)

Max Activating Token Index: 445

Text #6

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.9285. Min Act: -0.0000

Data Index: 365570 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8833. Min Act: -0.0000

Data Index: 944530 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8587. Min Act: -0.0000

Data Index: 400548 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1232089 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1324979 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8200. Min Act: -0.0000

Data Index: 114688 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8057. Min Act: -0.0000

Data Index: 876700 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8123. Min Act: -0.0000

Data Index: 513348 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8454. Min Act: -0.0000

Data Index: 621628 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8119. Min Act: -0.0000

Data Index: 533696 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8142. Min Act: -0.0000

Data Index: 526834 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1332826 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8145. Min Act: -0.0000

Data Index: 1348840 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.7476. Min Act: -0.0000

Data Index: 254755 (C4 (Web Text))

Max Activating Token Index: 201