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

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

Neuron 237 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: 0.0791. Min Range: -0.0791

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1314044 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0762. Min Act: -0.0002

Data Index: 587443 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1604194 (Python Code)

Max Activating Token Index: 304

Text #3

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1527629 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0700. Min Act: -0.0002

Data Index: 154971 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1438499 (Python Code)

Max Activating Token Index: 176

Text #6

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0694. Min Act: -0.0002

Data Index: 968638 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0692. Min Act: -0.0002

Data Index: 389478 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1462807 (Python Code)

Max Activating Token Index: 712

Text #9

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0701. Min Act: -0.0002

Data Index: 634088 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1261277 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1415716 (Python Code)

Max Activating Token Index: 921

Text #12

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0666. Min Act: -0.0002

Data Index: 401289 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1604453 (Python Code)

Max Activating Token Index: 702

Text #14

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0663. Min Act: -0.0002

Data Index: 413704 (C4 (Web Text))

Max Activating Token Index: 504

Text #15

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1362387 (Python Code)

Max Activating Token Index: 825

Text #16

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0664. Min Act: -0.0002

Data Index: 894539 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0656. Min Act: -0.0003

Data Index: 623928 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1591450 (Python Code)

Max Activating Token Index: 880

Text #19

Max Range: 0.0791. Min Range: -0.0791

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1550044 (Python Code)

Max Activating Token Index: 1010