Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3569 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4921. Min Act: -0.0001

Data Index: 359516 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4613. Min Act: -0.0001

Data Index: 1375838 (Python Code)

Max Activating Token Index: 855

Text #2

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1135084 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3992. Min Act: -0.0001

Data Index: 1143507 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1054198 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3785. Min Act: -0.0000

Data Index: 1398313 (Python Code)

Max Activating Token Index: 891

Text #6

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1415521 (Python Code)

Max Activating Token Index: 715

Text #7

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3724. Min Act: -0.0001

Data Index: 1637296 (Python Code)

Max Activating Token Index: 206

Text #8

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3721. Min Act: -0.0000

Data Index: 1609292 (Python Code)

Max Activating Token Index: 594

Text #9

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3590. Min Act: -0.0001

Data Index: 97128 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3533. Min Act: -0.0001

Data Index: 1467349 (Python Code)

Max Activating Token Index: 701

Text #11

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3543. Min Act: -0.0001

Data Index: 1228213 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3636. Min Act: -0.0001

Data Index: 1641552 (Python Code)

Max Activating Token Index: 902

Text #13

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3525. Min Act: -0.0001

Data Index: 1444411 (Python Code)

Max Activating Token Index: 959

Text #14

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3550. Min Act: -0.0000

Data Index: 131992 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3392. Min Act: -0.0001

Data Index: 1655878 (Python Code)

Max Activating Token Index: 816

Text #16

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3386. Min Act: -0.0001

Data Index: 1612859 (Python Code)

Max Activating Token Index: 831

Text #17

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3742. Min Act: -0.0001

Data Index: 499901 (C4 (Web Text))

Max Activating Token Index: 1017

Text #18

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1653982 (Python Code)

Max Activating Token Index: 549

Text #19

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3471. Min Act: -0.0001

Data Index: 1628606 (Python Code)

Max Activating Token Index: 201