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

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

Neuron 4735 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.1768. Min Act: -0.0000

Data Index: 1411811 (Python Code)

Max Activating Token Index: 946

Text #1

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1549112 (Python Code)

Max Activating Token Index: 159

Text #2

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1535822 (Python Code)

Max Activating Token Index: 999

Text #3

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1466339 (Python Code)

Max Activating Token Index: 932

Text #4

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8663. Min Act: -0.0000

Data Index: 1652752 (Python Code)

Max Activating Token Index: 534

Text #5

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1479862 (Python Code)

Max Activating Token Index: 626

Text #6

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1422198 (Python Code)

Max Activating Token Index: 153

Text #7

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9747. Min Act: -0.0000

Data Index: 1625416 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1653584 (Python Code)

Max Activating Token Index: 377

Text #9

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1446505 (Python Code)

Max Activating Token Index: 333

Text #10

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8699. Min Act: -0.0000

Data Index: 1465670 (Python Code)

Max Activating Token Index: 52

Text #11

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1368292 (Python Code)

Max Activating Token Index: 380

Text #12

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1637713 (Python Code)

Max Activating Token Index: 974

Text #13

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1439074 (Python Code)

Max Activating Token Index: 688

Text #14

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1601198 (Python Code)

Max Activating Token Index: 346

Text #15

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1452018 (Python Code)

Max Activating Token Index: 797

Text #16

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1498543 (Python Code)

Max Activating Token Index: 99

Text #17

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1552747 (Python Code)

Max Activating Token Index: 638

Text #18

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1583305 (Python Code)

Max Activating Token Index: 664

Text #19

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1506601 (Python Code)

Max Activating Token Index: 220