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

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

Neuron 1533 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.7363. Min Act: -0.0000

Data Index: 101685 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.6836. Min Act: -0.0000

Data Index: 1581552 (Python Code)

Max Activating Token Index: 988

Text #2

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.6473. Min Act: -0.0000

Data Index: 996279 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.6769. Min Act: -0.0000

Data Index: 1573219 (Python Code)

Max Activating Token Index: 509

Text #4

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.6197. Min Act: -0.0000

Data Index: 1055977 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.6437. Min Act: -0.0000

Data Index: 1606725 (Python Code)

Max Activating Token Index: 343

Text #6

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.7163. Min Act: -0.0000

Data Index: 1549384 (Python Code)

Max Activating Token Index: 609

Text #7

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.6572. Min Act: -0.0000

Data Index: 1437875 (Python Code)

Max Activating Token Index: 955

Text #8

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.5957. Min Act: -0.0000

Data Index: 1502619 (Python Code)

Max Activating Token Index: 675

Text #9

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.7270. Min Act: -0.0000

Data Index: 1396595 (Python Code)

Max Activating Token Index: 451

Text #10

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.5116. Min Act: -0.0000

Data Index: 404714 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.5972. Min Act: -0.0000

Data Index: 1626953 (Python Code)

Max Activating Token Index: 758

Text #12

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.4889. Min Act: -0.0000

Data Index: 1544959 (Python Code)

Max Activating Token Index: 874

Text #13

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.5957. Min Act: -0.0000

Data Index: 1539051 (Python Code)

Max Activating Token Index: 702

Text #14

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.5352. Min Act: -0.0000

Data Index: 1478260 (Python Code)

Max Activating Token Index: 156

Text #15

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.4460. Min Act: -0.0000

Data Index: 1497277 (Python Code)

Max Activating Token Index: 932

Text #16

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.5930. Min Act: -0.0000

Data Index: 1342133 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.5188. Min Act: -0.0000

Data Index: 1392694 (Python Code)

Max Activating Token Index: 994

Text #18

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.6163. Min Act: -0.0000

Data Index: 1449349 (Python Code)

Max Activating Token Index: 807

Text #19

Max Range: 1.7363. Min Range: -1.7363

Max Act: 1.4797. Min Act: -0.0000

Data Index: 1491852 (Python Code)

Max Activating Token Index: 280