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

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

Neuron 1497 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: 0.0841. Min Range: -0.0841

Max Act: 0.0841. Min Act: -0.0002

Data Index: 837487 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0751. Min Act: -0.0002

Data Index: 97221 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0726. Min Act: -0.0002

Data Index: 584602 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0737. Min Act: -0.0002

Data Index: 590749 (C4 (Web Text))

Max Activating Token Index: 943

Text #4

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0708. Min Act: -0.0002

Data Index: 78696 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0691. Min Act: -0.0002

Data Index: 585842 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0720. Min Act: -0.0002

Data Index: 259294 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0694. Min Act: -0.0002

Data Index: 352771 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0689. Min Act: -0.0003

Data Index: 337538 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0688. Min Act: -0.0002

Data Index: 802979 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0677. Min Act: -0.0002

Data Index: 849169 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0676. Min Act: -0.0002

Data Index: 957677 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1006238 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0667. Min Act: -0.0002

Data Index: 941087 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0645. Min Act: -0.0002

Data Index: 375747 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0657. Min Act: -0.0002

Data Index: 377886 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1274481 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0647. Min Act: -0.0003

Data Index: 883241 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0641. Min Act: -0.0002

Data Index: 84962 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.0841. Min Range: -0.0841

Max Act: 0.0649. Min Act: -0.0002

Data Index: 42851 (C4 (Web Text))

Max Activating Token Index: 1021