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

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

Neuron 50 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: 0.0955. Min Range: -0.0955

Max Act: 0.0955. Min Act: -0.0002

Data Index: 328754 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0932. Min Act: -0.0003

Data Index: 141749 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0855. Min Act: -0.0003

Data Index: 634953 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0860. Min Act: -0.0002

Data Index: 855349 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0830. Min Act: -0.0003

Data Index: 967747 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0809. Min Act: -0.0003

Data Index: 409800 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1103945 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0780. Min Act: -0.0003

Data Index: 20865 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0806. Min Act: -0.0002

Data Index: 781678 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0794. Min Act: -0.0002

Data Index: 15311 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0805. Min Act: -0.0003

Data Index: 1174067 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0808. Min Act: -0.0003

Data Index: 257887 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0776. Min Act: -0.0002

Data Index: 469883 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0772. Min Act: -0.0003

Data Index: 231390 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0765. Min Act: -0.0002

Data Index: 519668 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1101241 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1112961 (C4 (Web Text))

Max Activating Token Index: 580

Text #17

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0737. Min Act: -0.0002

Data Index: 897669 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0757. Min Act: -0.0002

Data Index: 810920 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0748. Min Act: -0.0003

Data Index: 434579 (C4 (Web Text))

Max Activating Token Index: 787