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

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

Neuron 3655 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0928. Min Range: -1.0928

Max Act: 1.0928. Min Act: -0.0000

Data Index: 1428104 (Python Code)

Max Activating Token Index: 52

Text #1

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9599. Min Act: -0.0000

Data Index: 1360219 (Python Code)

Max Activating Token Index: 613

Text #2

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1582909 (Python Code)

Max Activating Token Index: 869

Text #3

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.9192. Min Act: -0.0000

Data Index: 1561864 (Python Code)

Max Activating Token Index: 1000

Text #4

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8828. Min Act: -0.0000

Data Index: 1478302 (Python Code)

Max Activating Token Index: 652

Text #5

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8599. Min Act: -0.0000

Data Index: 1513786 (Python Code)

Max Activating Token Index: 730

Text #6

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.7990. Min Act: -0.0000

Data Index: 729486 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8680. Min Act: -0.0001

Data Index: 1557301 (Python Code)

Max Activating Token Index: 572

Text #8

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1496069 (Python Code)

Max Activating Token Index: 549

Text #9

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1510627 (Python Code)

Max Activating Token Index: 660

Text #10

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8287. Min Act: -0.0000

Data Index: 309095 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1397808 (Python Code)

Max Activating Token Index: 604

Text #12

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1385191 (Python Code)

Max Activating Token Index: 1003

Text #13

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1656940 (Python Code)

Max Activating Token Index: 502

Text #14

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8239. Min Act: -0.0001

Data Index: 1422568 (Python Code)

Max Activating Token Index: 371

Text #15

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.7945. Min Act: -0.0000

Data Index: 522012 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1605515 (Python Code)

Max Activating Token Index: 916

Text #17

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8921. Min Act: -0.0000

Data Index: 615541 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.8407. Min Act: -0.0001

Data Index: 1628998 (Python Code)

Max Activating Token Index: 331

Text #19

Max Range: 1.0928. Min Range: -1.0928

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1523463 (Python Code)

Max Activating Token Index: 572