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

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

Neuron 4904 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.4685. Min Act: -0.0000

Data Index: 1452104 (Python Code)

Max Activating Token Index: 598

Text #1

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1514858 (Python Code)

Max Activating Token Index: 130

Text #2

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.4052. Min Act: -0.0000

Data Index: 1538928 (Python Code)

Max Activating Token Index: 333

Text #3

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1423560 (Python Code)

Max Activating Token Index: 815

Text #4

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3806. Min Act: -0.0000

Data Index: 282143 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3670. Min Act: -0.0000

Data Index: 1396479 (Python Code)

Max Activating Token Index: 924

Text #6

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3741. Min Act: -0.0000

Data Index: 216914 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1580121 (Python Code)

Max Activating Token Index: 250

Text #8

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3606. Min Act: -0.0000

Data Index: 1642332 (Python Code)

Max Activating Token Index: 250

Text #9

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1493451 (Python Code)

Max Activating Token Index: 897

Text #10

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1547829 (Python Code)

Max Activating Token Index: 882

Text #11

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1388465 (Python Code)

Max Activating Token Index: 218

Text #12

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1643772 (Python Code)

Max Activating Token Index: 127

Text #13

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3634. Min Act: -0.0000

Data Index: 1544698 (Python Code)

Max Activating Token Index: 967

Text #14

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1574343 (Python Code)

Max Activating Token Index: 781

Text #15

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1516741 (Python Code)

Max Activating Token Index: 35

Text #16

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1594470 (Python Code)

Max Activating Token Index: 381

Text #17

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3570. Min Act: -0.0000

Data Index: 1566516 (Python Code)

Max Activating Token Index: 958

Text #18

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3565. Min Act: -0.0000

Data Index: 255927 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.4685. Min Range: -0.4685

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1605670 (Python Code)

Max Activating Token Index: 917