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

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

Neuron 4953 in Layer 0

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: 0.7817. Min Range: -0.7817

Max Act: 0.7817. Min Act: -0.0001

Data Index: 1526586 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.7598. Min Act: -0.0001

Data Index: 1501269 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.7479. Min Act: -0.0001

Data Index: 1533867 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.7397. Min Act: -0.0001

Data Index: 1411018 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.7427. Min Act: -0.0001

Data Index: 1423643 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.7224. Min Act: -0.0001

Data Index: 1551782 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6994. Min Act: -0.0001

Data Index: 1633185 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6852. Min Act: -0.0001

Data Index: 1652033 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6838. Min Act: -0.0001

Data Index: 1445250 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6861. Min Act: -0.0001

Data Index: 1480921 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6862. Min Act: -0.0001

Data Index: 1648726 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6770. Min Act: -0.0001

Data Index: 1573644 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6673. Min Act: -0.0001

Data Index: 1362733 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6673. Min Act: -0.0001

Data Index: 1493759 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6806. Min Act: -0.0001

Data Index: 1622975 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6778. Min Act: -0.0001

Data Index: 1616810 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6759. Min Act: -0.0001

Data Index: 1600257 (Python Code)

Max Activating Token Index: 22

Text #17

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6710. Min Act: -0.0001

Data Index: 1582800 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6742. Min Act: -0.0001

Data Index: 1598516 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.7817. Min Range: -0.7817

Max Act: 0.6689. Min Act: -0.0001

Data Index: 1500688 (Python Code)

Max Activating Token Index: 8