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

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

Neuron 5175 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: 0.7411. Min Range: -0.7411

Max Act: 0.7411. Min Act: -0.0001

Data Index: 630010 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6884. Min Act: -0.0001

Data Index: 877663 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6900. Min Act: -0.0001

Data Index: 331629 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6799. Min Act: -0.0001

Data Index: 303653 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6794. Min Act: -0.0001

Data Index: 237239 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6610. Min Act: -0.0001

Data Index: 896635 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6652. Min Act: -0.0001

Data Index: 971181 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6732. Min Act: -0.0001

Data Index: 895661 (C4 (Web Text))

Max Activating Token Index: 3

Text #8

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6743. Min Act: -0.0001

Data Index: 312865 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6590. Min Act: -0.0001

Data Index: 954360 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6631. Min Act: -0.0001

Data Index: 1114382 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6684. Min Act: -0.0001

Data Index: 817733 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6470. Min Act: -0.0001

Data Index: 244533 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6537. Min Act: -0.0001

Data Index: 83888 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6515. Min Act: -0.0001

Data Index: 743657 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6484. Min Act: -0.0002

Data Index: 975974 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6489. Min Act: -0.0001

Data Index: 867242 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6552. Min Act: -0.0001

Data Index: 1111145 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6425. Min Act: -0.0001

Data Index: 151756 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.7411. Min Range: -0.7411

Max Act: 0.6520. Min Act: -0.0001

Data Index: 421037 (C4 (Web Text))

Max Activating Token Index: 9