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

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

Neuron 478 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.9066. Min Act: 0.0000

Data Index: 1531054 (Python Code)

Max Activating Token Index: 401

Text #1

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.8568. Min Act: 0.0000

Data Index: 1396580 (Python Code)

Max Activating Token Index: 390

Text #2

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.8400. Min Act: 0.0000

Data Index: 1412188 (Python Code)

Max Activating Token Index: 696

Text #3

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.8170. Min Act: 0.0000

Data Index: 1635043 (Python Code)

Max Activating Token Index: 493

Text #4

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1602514 (Python Code)

Max Activating Token Index: 941

Text #5

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7557. Min Act: 0.0000

Data Index: 1597044 (Python Code)

Max Activating Token Index: 594

Text #6

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1393415 (Python Code)

Max Activating Token Index: 319

Text #7

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1603992 (Python Code)

Max Activating Token Index: 634

Text #8

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7333. Min Act: 0.0000

Data Index: 1593144 (Python Code)

Max Activating Token Index: 884

Text #9

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1622255 (Python Code)

Max Activating Token Index: 872

Text #10

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7041. Min Act: 0.0000

Data Index: 1471778 (Python Code)

Max Activating Token Index: 871

Text #11

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7112. Min Act: -0.0000

Data Index: 829572 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6685. Min Act: 0.0000

Data Index: 1566535 (Python Code)

Max Activating Token Index: 391

Text #13

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6838. Min Act: 0.0000

Data Index: 1395753 (Python Code)

Max Activating Token Index: 777

Text #14

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.7479. Min Act: 0.0000

Data Index: 1501419 (Python Code)

Max Activating Token Index: 871

Text #15

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6569. Min Act: 0.0000

Data Index: 1458077 (Python Code)

Max Activating Token Index: 144

Text #16

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6664. Min Act: 0.0000

Data Index: 1471970 (Python Code)

Max Activating Token Index: 407

Text #17

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6612. Min Act: 0.0000

Data Index: 1603382 (Python Code)

Max Activating Token Index: 140

Text #18

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6623. Min Act: 0.0000

Data Index: 1501601 (Python Code)

Max Activating Token Index: 447

Text #19

Max Range: 0.9066. Min Range: -0.9066

Max Act: 0.6413. Min Act: 0.0000

Data Index: 1416723 (Python Code)

Max Activating Token Index: 571