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

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

Neuron 2791 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0457. Min Range: -1.0457

Max Act: 1.0457. Min Act: -0.0000

Data Index: 1616280 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.9235. Min Act: -0.0000

Data Index: 1517060 (Python Code)

Max Activating Token Index: 168

Text #2

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.9139. Min Act: -0.0000

Data Index: 1541331 (Python Code)

Max Activating Token Index: 942

Text #3

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.9093. Min Act: -0.0000

Data Index: 1636517 (Python Code)

Max Activating Token Index: 631

Text #4

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1588506 (Python Code)

Max Activating Token Index: 840

Text #5

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.9307. Min Act: -0.0000

Data Index: 1577759 (Python Code)

Max Activating Token Index: 787

Text #6

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1423647 (Python Code)

Max Activating Token Index: 25

Text #7

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8275. Min Act: -0.0000

Data Index: 1494018 (Python Code)

Max Activating Token Index: 1017

Text #8

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8998. Min Act: -0.0000

Data Index: 1387281 (Python Code)

Max Activating Token Index: 138

Text #9

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1364564 (Python Code)

Max Activating Token Index: 996

Text #10

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1651867 (Python Code)

Max Activating Token Index: 696

Text #11

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1611277 (Python Code)

Max Activating Token Index: 765

Text #12

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1376277 (Python Code)

Max Activating Token Index: 182

Text #13

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1513035 (Python Code)

Max Activating Token Index: 48

Text #14

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8117. Min Act: -0.0001

Data Index: 1491217 (Python Code)

Max Activating Token Index: 1003

Text #15

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1601604 (Python Code)

Max Activating Token Index: 867

Text #16

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1480671 (Python Code)

Max Activating Token Index: 759

Text #17

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.8972. Min Act: -0.0000

Data Index: 1642468 (Python Code)

Max Activating Token Index: 792

Text #18

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1558975 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 1.0457. Min Range: -1.0457

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1583906 (Python Code)

Max Activating Token Index: 526