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

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

Neuron 3728 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: 0.0690. Min Range: -0.0690

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1577387 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0673. Min Act: -0.0001

Data Index: 1599118 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0649. Min Act: -0.0001

Data Index: 1374875 (Python Code)

Max Activating Token Index: 785

Text #3

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1394066 (Python Code)

Max Activating Token Index: 539

Text #4

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1388419 (Python Code)

Max Activating Token Index: 405

Text #5

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1378383 (Python Code)

Max Activating Token Index: 287

Text #6

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0613. Min Act: -0.0001

Data Index: 1457499 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1653802 (Python Code)

Max Activating Token Index: 291

Text #8

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1416306 (Python Code)

Max Activating Token Index: 428

Text #9

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1359858 (Python Code)

Max Activating Token Index: 249

Text #10

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1499482 (Python Code)

Max Activating Token Index: 562

Text #11

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1436854 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1514808 (Python Code)

Max Activating Token Index: 309

Text #13

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1531645 (Python Code)

Max Activating Token Index: 788

Text #14

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1490225 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1655607 (Python Code)

Max Activating Token Index: 659

Text #16

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1514588 (Python Code)

Max Activating Token Index: 447

Text #17

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0604. Min Act: -0.0001

Data Index: 1472255 (Python Code)

Max Activating Token Index: 654

Text #18

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1376185 (Python Code)

Max Activating Token Index: 403

Text #19

Max Range: 0.0690. Min Range: -0.0690

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1370342 (Python Code)

Max Activating Token Index: 478