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

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

Neuron 5163 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: 1.0611. Min Range: -1.0611

Max Act: 1.0611. Min Act: -0.0001

Data Index: 737613 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9820. Min Act: -0.0001

Data Index: 452351 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9686. Min Act: -0.0001

Data Index: 549294 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9814. Min Act: -0.0001

Data Index: 1346461 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9259. Min Act: -0.0001

Data Index: 345044 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9328. Min Act: -0.0001

Data Index: 1127445 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9169. Min Act: -0.0001

Data Index: 516342 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9163. Min Act: -0.0001

Data Index: 1062512 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.9147. Min Act: -0.0001

Data Index: 373976 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8674. Min Act: -0.0001

Data Index: 1142202 (C4 (Web Text))

Max Activating Token Index: 657

Text #10

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8766. Min Act: -0.0001

Data Index: 574317 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8602. Min Act: -0.0001

Data Index: 794938 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8654. Min Act: -0.0001

Data Index: 35177 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8684. Min Act: -0.0001

Data Index: 38003 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8556. Min Act: -0.0001

Data Index: 394302 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8631. Min Act: -0.0001

Data Index: 465333 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8690. Min Act: -0.0001

Data Index: 403811 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8357. Min Act: -0.0001

Data Index: 354983 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8598. Min Act: -0.0001

Data Index: 853446 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 1.0611. Min Range: -1.0611

Max Act: 0.8402. Min Act: -0.0001

Data Index: 146928 (C4 (Web Text))

Max Activating Token Index: 53