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

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

Neuron 1949 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: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0002

Data Index: 655543 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0001. Min Act: -0.0002

Data Index: 1180582 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1388406 (Python Code)

Max Activating Token Index: 960

Text #3

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 652910 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 690012 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1055617 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1133603 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0003

Data Index: 725085 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0003

Data Index: 1081523 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0003

Data Index: 941335 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0003

Data Index: 82065 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1040987 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 425535 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 591838 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 681463 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0003

Data Index: 266803 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 656655 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0003

Data Index: 439032 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 438328 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0001. Min Range: -0.0001

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1423784 (Python Code)

Max Activating Token Index: 1023