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

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

Neuron 1664 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.1817. Min Act: -0.0000

Data Index: 1360619 (Python Code)

Max Activating Token Index: 844

Text #1

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.3644. Min Act: -0.0000

Data Index: 1058850 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.3839. Min Act: -0.0000

Data Index: 1587139 (Python Code)

Max Activating Token Index: 511

Text #3

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.3665. Min Act: -0.0000

Data Index: 1589930 (Python Code)

Max Activating Token Index: 693

Text #4

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.2103. Min Act: -0.0000

Data Index: 1137292 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.1453. Min Act: -0.0000

Data Index: 638710 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.2142. Min Act: -0.0000

Data Index: 1157368 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.1823. Min Act: -0.0000

Data Index: 699695 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.0526. Min Act: -0.0000

Data Index: 651990 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.0525. Min Act: -0.0000

Data Index: 115609 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.0066. Min Act: -0.0000

Data Index: 278875 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.1568. Min Act: -0.0000

Data Index: 955785 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.1002. Min Act: -0.0000

Data Index: 667705 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1340606 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1068592 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.0403. Min Act: -0.0000

Data Index: 20623 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 1.3839. Min Range: -1.3839

Max Act: 0.9476. Min Act: -0.0000

Data Index: 1315730 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 1.3839. Min Range: -1.3839

Max Act: 1.0002. Min Act: -0.0000

Data Index: 927352 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 1.3839. Min Range: -1.3839

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1619506 (Python Code)

Max Activating Token Index: 404

Text #19

Max Range: 1.3839. Min Range: -1.3839

Max Act: 0.9862. Min Act: -0.0000

Data Index: 778335 (C4 (Web Text))

Max Activating Token Index: 38