Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 9 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.5733. Min Act: -0.0001

Data Index: 1363339 (Python Code)

Max Activating Token Index: 835

Text #1

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.5800. Min Act: -0.0000

Data Index: 1593452 (Python Code)

Max Activating Token Index: 552

Text #2

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.2971. Min Act: -0.0001

Data Index: 1436081 (Python Code)

Max Activating Token Index: 486

Text #3

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.1875. Min Act: -0.0000

Data Index: 1479758 (Python Code)

Max Activating Token Index: 678

Text #4

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.1740. Min Act: -0.0001

Data Index: 1517623 (Python Code)

Max Activating Token Index: 924

Text #5

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.1348. Min Act: -0.0001

Data Index: 1639528 (Python Code)

Max Activating Token Index: 34

Text #6

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.1150. Min Act: -0.0001

Data Index: 1382600 (Python Code)

Max Activating Token Index: 871

Text #7

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.1167. Min Act: -0.0001

Data Index: 1638915 (Python Code)

Max Activating Token Index: 392

Text #8

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.0719. Min Act: -0.0001

Data Index: 1428024 (Python Code)

Max Activating Token Index: 716

Text #9

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.0567. Min Act: -0.0001

Data Index: 1419455 (Python Code)

Max Activating Token Index: 816

Text #10

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.0944. Min Act: -0.0001

Data Index: 1585788 (Python Code)

Max Activating Token Index: 676

Text #11

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.0261. Min Act: -0.0001

Data Index: 1464163 (Python Code)

Max Activating Token Index: 372

Text #12

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.0566. Min Act: -0.0001

Data Index: 1476669 (Python Code)

Max Activating Token Index: 304

Text #13

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.0089. Min Act: -0.0001

Data Index: 1451899 (Python Code)

Max Activating Token Index: 83

Text #14

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.0719. Min Act: -0.0000

Data Index: 1517242 (Python Code)

Max Activating Token Index: 376

Text #15

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.0236. Min Act: -0.0001

Data Index: 1578769 (Python Code)

Max Activating Token Index: 293

Text #16

Max Range: 1.5800. Min Range: -1.5800

Max Act: 0.9870. Min Act: -0.0001

Data Index: 1568375 (Python Code)

Max Activating Token Index: 217

Text #17

Max Range: 1.5800. Min Range: -1.5800

Max Act: 1.0024. Min Act: -0.0001

Data Index: 1387125 (Python Code)

Max Activating Token Index: 696

Text #18

Max Range: 1.5800. Min Range: -1.5800

Max Act: 0.9986. Min Act: -0.0001

Data Index: 1426102 (Python Code)

Max Activating Token Index: 903

Text #19

Max Range: 1.5800. Min Range: -1.5800

Max Act: 0.9981. Min Act: -0.0001

Data Index: 1502638 (Python Code)

Max Activating Token Index: 439