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

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

Neuron 5945 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: 1.0684. Min Range: -1.0684

Max Act: 1.0684. Min Act: -0.0002

Data Index: 850157 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0673. Min Act: -0.0002

Data Index: 898430 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0457. Min Act: -0.0002

Data Index: 439756 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0325. Min Act: -0.0002

Data Index: 287642 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0002. Min Act: -0.0002

Data Index: 256011 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9964. Min Act: -0.0002

Data Index: 536940 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0080. Min Act: -0.0002

Data Index: 861095 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0236. Min Act: -0.0002

Data Index: 679629 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0042. Min Act: -0.0002

Data Index: 1004000 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0308. Min Act: -0.0003

Data Index: 337564 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0068. Min Act: -0.0002

Data Index: 921825 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0101. Min Act: -0.0002

Data Index: 1204748 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0294. Min Act: -0.0002

Data Index: 1316883 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9774. Min Act: -0.0002

Data Index: 1072107 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0117. Min Act: -0.0002

Data Index: 1089740 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0050. Min Act: -0.0002

Data Index: 1024960 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 1.0684. Min Range: -1.0684

Max Act: 1.0016. Min Act: -0.0002

Data Index: 1242584 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9947. Min Act: -0.0002

Data Index: 874912 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9826. Min Act: -0.0002

Data Index: 704658 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 1.0684. Min Range: -1.0684

Max Act: 0.9777. Min Act: -0.0002

Data Index: 358499 (C4 (Web Text))

Max Activating Token Index: 149