Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5071 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0014. Min Act: -0.0002

Data Index: 1384296 (Python Code)

Max Activating Token Index: 611

Text #1

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0011. Min Act: -0.0002

Data Index: 149569 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0012. Min Act: -0.0002

Data Index: 627337 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1207661 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1220404 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0011. Min Act: -0.0002

Data Index: 293686 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0011. Min Act: -0.0002

Data Index: 1649298 (Python Code)

Max Activating Token Index: 674

Text #7

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0011. Min Act: -0.0002

Data Index: 509095 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0010. Min Act: -0.0002

Data Index: 909661 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0010. Min Act: -0.0002

Data Index: 822636 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1402619 (Python Code)

Max Activating Token Index: 537

Text #11

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0010. Min Act: -0.0002

Data Index: 101569 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1530449 (Python Code)

Max Activating Token Index: 773

Text #13

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0010. Min Act: -0.0002

Data Index: 954860 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0010. Min Act: -0.0002

Data Index: 300161 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0010. Min Act: -0.0002

Data Index: 406119 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0010. Min Act: -0.0002

Data Index: 684698 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0010. Min Act: -0.0002

Data Index: 483622 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1351353 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.0014. Min Range: -0.0014

Max Act: 0.0010. Min Act: -0.0002

Data Index: 320811 (C4 (Web Text))

Max Activating Token Index: 506