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

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

Neuron 1031 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1325030 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0685. Min Act: -0.0000

Data Index: 1260917 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0655. Min Act: -0.0000

Data Index: 67104 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0593. Min Act: -0.0000

Data Index: 335503 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0597. Min Act: -0.0000

Data Index: 1017807 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0555. Min Act: -0.0000

Data Index: 513089 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0552. Min Act: -0.0000

Data Index: 856438 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0520. Min Act: -0.0000

Data Index: 505680 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0530. Min Act: -0.0000

Data Index: 544815 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0529. Min Act: -0.0000

Data Index: 1288535 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0528. Min Act: -0.0000

Data Index: 841653 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1019635 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0494. Min Act: -0.0000

Data Index: 64333 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0473. Min Act: -0.0000

Data Index: 1429764 (Python Code)

Max Activating Token Index: 230

Text #14

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0502. Min Act: -0.0000

Data Index: 438 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0492. Min Act: -0.0000

Data Index: 1270604 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0491. Min Act: -0.0000

Data Index: 893225 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0526. Min Act: -0.0000

Data Index: 1126230 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0498. Min Act: -0.0000

Data Index: 281083 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 0.0785. Min Range: -0.0785

Max Act: 0.0464. Min Act: -0.0000

Data Index: 915568 (C4 (Web Text))

Max Activating Token Index: 426