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

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

Neuron 2000 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1581970 (Python Code)

Max Activating Token Index: 1000

Text #1

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2618. Min Act: -0.0001

Data Index: 1547308 (Python Code)

Max Activating Token Index: 495

Text #2

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2621. Min Act: -0.0000

Data Index: 1564799 (Python Code)

Max Activating Token Index: 37

Text #3

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1581296 (Python Code)

Max Activating Token Index: 995

Text #4

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2678. Min Act: -0.0001

Data Index: 1453519 (Python Code)

Max Activating Token Index: 309

Text #5

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2645. Min Act: -0.0001

Data Index: 1506724 (Python Code)

Max Activating Token Index: 798

Text #6

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1442786 (Python Code)

Max Activating Token Index: 210

Text #7

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2411. Min Act: -0.0000

Data Index: 1618884 (Python Code)

Max Activating Token Index: 165

Text #8

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1391835 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2574. Min Act: -0.0001

Data Index: 1453456 (Python Code)

Max Activating Token Index: 715

Text #10

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1628600 (Python Code)

Max Activating Token Index: 446

Text #11

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2468. Min Act: -0.0000

Data Index: 1507858 (Python Code)

Max Activating Token Index: 473

Text #12

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2532. Min Act: -0.0001

Data Index: 1529695 (Python Code)

Max Activating Token Index: 536

Text #13

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1511112 (Python Code)

Max Activating Token Index: 211

Text #14

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1435405 (Python Code)

Max Activating Token Index: 278

Text #15

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2445. Min Act: -0.0001

Data Index: 1577781 (Python Code)

Max Activating Token Index: 556

Text #16

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1636096 (Python Code)

Max Activating Token Index: 668

Text #17

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2555. Min Act: -0.0001

Data Index: 1541004 (Python Code)

Max Activating Token Index: 601

Text #18

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2322. Min Act: -0.0001

Data Index: 1645096 (Python Code)

Max Activating Token Index: 959

Text #19

Max Range: 0.2921. Min Range: -0.2921

Max Act: 0.2306. Min Act: -0.0001

Data Index: 1582696 (Python Code)

Max Activating Token Index: 406