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

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

Neuron 4514 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: 0.7392. Min Range: -0.7392

Max Act: 0.7392. Min Act: -0.0000

Data Index: 1541376 (Python Code)

Max Activating Token Index: 264

Text #1

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.6042. Min Act: -0.0000

Data Index: 1556081 (Python Code)

Max Activating Token Index: 741

Text #2

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1508531 (Python Code)

Max Activating Token Index: 111

Text #3

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1475262 (Python Code)

Max Activating Token Index: 159

Text #4

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1403033 (Python Code)

Max Activating Token Index: 918

Text #5

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1596823 (Python Code)

Max Activating Token Index: 820

Text #6

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1617027 (Python Code)

Max Activating Token Index: 820

Text #7

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1594319 (Python Code)

Max Activating Token Index: 836

Text #8

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1503221 (Python Code)

Max Activating Token Index: 1016

Text #9

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.4929. Min Act: -0.0000

Data Index: 1437866 (Python Code)

Max Activating Token Index: 253

Text #10

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1516266 (Python Code)

Max Activating Token Index: 758

Text #11

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1400080 (Python Code)

Max Activating Token Index: 572

Text #12

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.4161. Min Act: -0.0000

Data Index: 1537239 (Python Code)

Max Activating Token Index: 981

Text #13

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.4406. Min Act: -0.0000

Data Index: 1378518 (Python Code)

Max Activating Token Index: 539

Text #14

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1526766 (Python Code)

Max Activating Token Index: 961

Text #15

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1595301 (Python Code)

Max Activating Token Index: 775

Text #16

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1640418 (Python Code)

Max Activating Token Index: 239

Text #17

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1562910 (Python Code)

Max Activating Token Index: 604

Text #18

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.4128. Min Act: -0.0000

Data Index: 1372972 (Python Code)

Max Activating Token Index: 625

Text #19

Max Range: 0.7392. Min Range: -0.7392

Max Act: 0.3801. Min Act: -0.0000

Data Index: 1490181 (Python Code)

Max Activating Token Index: 918