Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2164 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.2047. Min Act: -0.0001

Data Index: 1464333 (Python Code)

Max Activating Token Index: 256

Text #1

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1997. Min Act: -0.0001

Data Index: 1586264 (Python Code)

Max Activating Token Index: 711

Text #2

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1604482 (Python Code)

Max Activating Token Index: 763

Text #3

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1920. Min Act: -0.0001

Data Index: 1591323 (Python Code)

Max Activating Token Index: 829

Text #4

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1867. Min Act: -0.0001

Data Index: 1384226 (Python Code)

Max Activating Token Index: 734

Text #5

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1524796 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1849. Min Act: -0.0001

Data Index: 1644468 (Python Code)

Max Activating Token Index: 1000

Text #7

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1787. Min Act: -0.0001

Data Index: 1530255 (Python Code)

Max Activating Token Index: 1022

Text #8

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1777. Min Act: -0.0001

Data Index: 1412783 (Python Code)

Max Activating Token Index: 124

Text #9

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1567424 (Python Code)

Max Activating Token Index: 946

Text #10

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1487327 (Python Code)

Max Activating Token Index: 624

Text #11

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1504591 (Python Code)

Max Activating Token Index: 851

Text #12

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1652. Min Act: -0.0001

Data Index: 1628862 (Python Code)

Max Activating Token Index: 163

Text #13

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1662. Min Act: -0.0001

Data Index: 1395787 (Python Code)

Max Activating Token Index: 770

Text #14

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1663. Min Act: -0.0001

Data Index: 1607846 (Python Code)

Max Activating Token Index: 369

Text #15

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1633. Min Act: -0.0001

Data Index: 1421936 (Python Code)

Max Activating Token Index: 640

Text #16

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1443047 (Python Code)

Max Activating Token Index: 1013

Text #17

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1578. Min Act: -0.0001

Data Index: 1478695 (Python Code)

Max Activating Token Index: 966

Text #18

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1616813 (Python Code)

Max Activating Token Index: 829

Text #19

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1595. Min Act: -0.0001

Data Index: 1392036 (Python Code)

Max Activating Token Index: 876