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

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

Neuron 127 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: 1.0643. Min Range: -1.0643

Max Act: 1.0643. Min Act: -0.0002

Data Index: 579758 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 1.0643. Min Range: -1.0643

Max Act: 1.0511. Min Act: -0.0002

Data Index: 811565 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 1.0643. Min Range: -1.0643

Max Act: 1.0635. Min Act: -0.0002

Data Index: 244950 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 1.0643. Min Range: -1.0643

Max Act: 1.0426. Min Act: -0.0002

Data Index: 930967 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 1.0643. Min Range: -1.0643

Max Act: 1.0308. Min Act: -0.0002

Data Index: 507900 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 1.0643. Min Range: -1.0643

Max Act: 1.0233. Min Act: -0.0003

Data Index: 1295985 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9869. Min Act: -0.0002

Data Index: 20644 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 1.0643. Min Range: -1.0643

Max Act: 1.0008. Min Act: -0.0003

Data Index: 21880 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9803. Min Act: -0.0002

Data Index: 3986 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9994. Min Act: -0.0002

Data Index: 1085983 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9932. Min Act: -0.0002

Data Index: 1047729 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9819. Min Act: -0.0003

Data Index: 916798 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9673. Min Act: -0.0002

Data Index: 819957 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9890. Min Act: -0.0002

Data Index: 536833 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9734. Min Act: -0.0002

Data Index: 888383 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9589. Min Act: -0.0002

Data Index: 1280582 (C4 (Web Text))

Max Activating Token Index: 454

Text #16

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9422. Min Act: -0.0002

Data Index: 1141057 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9632. Min Act: -0.0002

Data Index: 935699 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9684. Min Act: -0.0002

Data Index: 1010824 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 1.0643. Min Range: -1.0643

Max Act: 0.9515. Min Act: -0.0002

Data Index: 328029 (C4 (Web Text))

Max Activating Token Index: 743