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

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

Neuron 1977 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1436515 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.1384. Min Act: -0.0000

Data Index: 1555112 (Python Code)

Max Activating Token Index: 712

Text #2

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.1740. Min Act: -0.0000

Data Index: 1442695 (Python Code)

Max Activating Token Index: 708

Text #3

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0795. Min Act: -0.0000

Data Index: 1564747 (Python Code)

Max Activating Token Index: 815

Text #4

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0949. Min Act: -0.0000

Data Index: 1446897 (Python Code)

Max Activating Token Index: 64

Text #5

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0937. Min Act: -0.0000

Data Index: 1522545 (Python Code)

Max Activating Token Index: 842

Text #6

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0564. Min Act: -0.0000

Data Index: 1418826 (Python Code)

Max Activating Token Index: 902

Text #7

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0879. Min Act: -0.0000

Data Index: 1464519 (Python Code)

Max Activating Token Index: 616

Text #8

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1550574 (Python Code)

Max Activating Token Index: 827

Text #9

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0984. Min Act: -0.0000

Data Index: 1515888 (Python Code)

Max Activating Token Index: 238

Text #10

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0547. Min Act: -0.0000

Data Index: 1536769 (Python Code)

Max Activating Token Index: 822

Text #11

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0127. Min Act: -0.0000

Data Index: 1645333 (Python Code)

Max Activating Token Index: 795

Text #12

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0354. Min Act: -0.0000

Data Index: 1543357 (Python Code)

Max Activating Token Index: 550

Text #13

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1386412 (Python Code)

Max Activating Token Index: 360

Text #14

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0532. Min Act: -0.0000

Data Index: 1465213 (Python Code)

Max Activating Token Index: 452

Text #15

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0335. Min Act: -0.0000

Data Index: 1383611 (Python Code)

Max Activating Token Index: 929

Text #16

Max Range: 1.1740. Min Range: -1.1740

Max Act: 1.0342. Min Act: -0.0000

Data Index: 1537339 (Python Code)

Max Activating Token Index: 613

Text #17

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1630533 (Python Code)

Max Activating Token Index: 494

Text #18

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.9462. Min Act: -0.0000

Data Index: 1620107 (Python Code)

Max Activating Token Index: 371

Text #19

Max Range: 1.1740. Min Range: -1.1740

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1171129 (C4 (Web Text))

Max Activating Token Index: 211