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

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

Neuron 3239 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.9031. Min Act: -0.0000

Data Index: 1510734 (Python Code)

Max Activating Token Index: 373

Text #1

Max Range: 2.0890. Min Range: -2.0890

Max Act: 2.0890. Min Act: -0.0000

Data Index: 1592441 (Python Code)

Max Activating Token Index: 200

Text #2

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.9151. Min Act: -0.0000

Data Index: 867419 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 2.0890. Min Range: -2.0890

Max Act: 2.0615. Min Act: -0.0000

Data Index: 1540121 (Python Code)

Max Activating Token Index: 246

Text #4

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.7987. Min Act: -0.0000

Data Index: 1366580 (Python Code)

Max Activating Token Index: 734

Text #5

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.5633. Min Act: -0.0000

Data Index: 1479733 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.9663. Min Act: -0.0000

Data Index: 1564526 (Python Code)

Max Activating Token Index: 900

Text #7

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.8156. Min Act: -0.0000

Data Index: 1598246 (Python Code)

Max Activating Token Index: 922

Text #8

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.9154. Min Act: -0.0000

Data Index: 1042655 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.7832. Min Act: -0.0000

Data Index: 1467906 (Python Code)

Max Activating Token Index: 790

Text #10

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.9039. Min Act: -0.0000

Data Index: 1615543 (Python Code)

Max Activating Token Index: 967

Text #11

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.6743. Min Act: -0.0000

Data Index: 1637356 (Python Code)

Max Activating Token Index: 632

Text #12

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.7210. Min Act: -0.0000

Data Index: 942405 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.7261. Min Act: -0.0000

Data Index: 541316 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.8060. Min Act: -0.0000

Data Index: 1603668 (Python Code)

Max Activating Token Index: 860

Text #15

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.8373. Min Act: -0.0000

Data Index: 1656374 (Python Code)

Max Activating Token Index: 815

Text #16

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.7266. Min Act: -0.0000

Data Index: 1371063 (Python Code)

Max Activating Token Index: 682

Text #17

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.6776. Min Act: -0.0000

Data Index: 1389200 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.6740. Min Act: -0.0000

Data Index: 1582606 (Python Code)

Max Activating Token Index: 808

Text #19

Max Range: 2.0890. Min Range: -2.0890

Max Act: 1.6961. Min Act: -0.0000

Data Index: 1379654 (Python Code)

Max Activating Token Index: 749