Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3926 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1960. Min Range: -1.1960

Max Act: 1.1960. Min Act: -0.0000

Data Index: 185351 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 1.1960. Min Range: -1.1960

Max Act: 1.1537. Min Act: -0.0000

Data Index: 1064688 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.9983. Min Act: -0.0000

Data Index: 851469 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.9461. Min Act: -0.0001

Data Index: 521136 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1211086 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.9413. Min Act: -0.0000

Data Index: 519398 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.9069. Min Act: -0.0000

Data Index: 1283523 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.9028. Min Act: -0.0000

Data Index: 288764 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.9041. Min Act: -0.0000

Data Index: 246490 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.9014. Min Act: -0.0000

Data Index: 78019 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8632. Min Act: -0.0000

Data Index: 257773 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.9036. Min Act: -0.0000

Data Index: 196584 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8297. Min Act: -0.0000

Data Index: 402650 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8703. Min Act: -0.0000

Data Index: 581657 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8651. Min Act: -0.0000

Data Index: 699883 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8597. Min Act: -0.0001

Data Index: 1214649 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1038405 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8419. Min Act: -0.0000

Data Index: 754454 (C4 (Web Text))

Max Activating Token Index: 513

Text #18

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8642. Min Act: -0.0001

Data Index: 1102850 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 1.1960. Min Range: -1.1960

Max Act: 0.8185. Min Act: -0.0000

Data Index: 1247421 (C4 (Web Text))

Max Activating Token Index: 985