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

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

Neuron 1923 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: 0.0986. Min Range: -0.0986

Max Act: 0.0986. Min Act: -0.0001

Data Index: 231262 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0868. Min Act: -0.0001

Data Index: 791769 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0777. Min Act: -0.0001

Data Index: 998035 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0773. Min Act: -0.0001

Data Index: 717919 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0787. Min Act: -0.0001

Data Index: 173430 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0757. Min Act: -0.0001

Data Index: 927622 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0752. Min Act: -0.0001

Data Index: 77618 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0729. Min Act: -0.0001

Data Index: 831484 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0714. Min Act: -0.0001

Data Index: 1003774 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0712. Min Act: -0.0001

Data Index: 713102 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0706. Min Act: -0.0001

Data Index: 47942 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0700. Min Act: -0.0001

Data Index: 8546 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0666. Min Act: -0.0001

Data Index: 164159 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0641. Min Act: -0.0001

Data Index: 691410 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1277859 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0609. Min Act: -0.0001

Data Index: 214202 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0600. Min Act: -0.0001

Data Index: 438478 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0589. Min Act: -0.0001

Data Index: 1316538 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0589. Min Act: -0.0001

Data Index: 762524 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0986. Min Range: -0.0986

Max Act: 0.0577. Min Act: -0.0001

Data Index: 365597 (C4 (Web Text))

Max Activating Token Index: 1023