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

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

Neuron 5584 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: 1.4721. Min Range: -1.4721

Max Act: 1.4721. Min Act: -0.0003

Data Index: 1159495 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.4232. Min Act: -0.0002

Data Index: 552402 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.3027. Min Act: -0.0002

Data Index: 1380211 (Python Code)

Max Activating Token Index: 692

Text #3

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.3022. Min Act: -0.0002

Data Index: 1456833 (Python Code)

Max Activating Token Index: 324

Text #4

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.2668. Min Act: -0.0002

Data Index: 911948 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.2625. Min Act: -0.0002

Data Index: 1606990 (Python Code)

Max Activating Token Index: 285

Text #6

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.2664. Min Act: -0.0002

Data Index: 1432656 (Python Code)

Max Activating Token Index: 91

Text #7

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.2315. Min Act: -0.0002

Data Index: 711956 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.2424. Min Act: -0.0002

Data Index: 1406556 (Python Code)

Max Activating Token Index: 609

Text #9

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.2447. Min Act: -0.0002

Data Index: 1428603 (Python Code)

Max Activating Token Index: 345

Text #10

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1880. Min Act: -0.0002

Data Index: 821396 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.2201. Min Act: -0.0002

Data Index: 881458 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1881. Min Act: -0.0002

Data Index: 1521632 (Python Code)

Max Activating Token Index: 313

Text #13

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1918. Min Act: -0.0002

Data Index: 1395097 (Python Code)

Max Activating Token Index: 485

Text #14

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.2047. Min Act: -0.0002

Data Index: 1553923 (Python Code)

Max Activating Token Index: 401

Text #15

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.2101. Min Act: -0.0002

Data Index: 648527 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1665. Min Act: -0.0002

Data Index: 932178 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1735. Min Act: -0.0002

Data Index: 1378081 (Python Code)

Max Activating Token Index: 644

Text #18

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1568. Min Act: -0.0002

Data Index: 1402974 (Python Code)

Max Activating Token Index: 713

Text #19

Max Range: 1.4721. Min Range: -1.4721

Max Act: 1.1534. Min Act: -0.0002

Data Index: 16972 (C4 (Web Text))

Max Activating Token Index: 660