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

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

Neuron 6022 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: 0.1034. Min Range: -0.1034

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1606578 (Python Code)

Max Activating Token Index: 788

Text #1

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0529. Min Act: -0.0000

Data Index: 919842 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0466. Min Act: -0.0000

Data Index: 80747 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0443. Min Act: -0.0000

Data Index: 123950 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0445. Min Act: -0.0000

Data Index: 608928 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0439. Min Act: -0.0000

Data Index: 1224877 (C4 (Web Text))

Max Activating Token Index: 542

Text #6

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0435. Min Act: -0.0000

Data Index: 306787 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0401. Min Act: -0.0000

Data Index: 371829 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0425. Min Act: -0.0000

Data Index: 807673 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0419. Min Act: -0.0000

Data Index: 598184 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0417. Min Act: -0.0000

Data Index: 420542 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0371. Min Act: -0.0000

Data Index: 1017569 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0397. Min Act: -0.0000

Data Index: 1629881 (Python Code)

Max Activating Token Index: 748

Text #13

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0389. Min Act: -0.0000

Data Index: 337609 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0360. Min Act: -0.0000

Data Index: 463941 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0376. Min Act: -0.0000

Data Index: 445636 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0375. Min Act: -0.0000

Data Index: 1582269 (Python Code)

Max Activating Token Index: 990

Text #17

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0366. Min Act: -0.0000

Data Index: 1050208 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0366. Min Act: -0.0000

Data Index: 223645 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.1034. Min Range: -0.1034

Max Act: 0.0366. Min Act: -0.0000

Data Index: 758079 (C4 (Web Text))

Max Activating Token Index: 376