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

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

Neuron 144 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1818. Min Act: -0.0001

Data Index: 1576334 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1432. Min Act: -0.0001

Data Index: 1508134 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1415688 (Python Code)

Max Activating Token Index: 73

Text #3

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1033. Min Act: -0.0001

Data Index: 1368658 (Python Code)

Max Activating Token Index: 191

Text #4

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1629235 (Python Code)

Max Activating Token Index: 311

Text #5

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1547747 (Python Code)

Max Activating Token Index: 502

Text #6

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1625808 (Python Code)

Max Activating Token Index: 48

Text #7

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1361903 (Python Code)

Max Activating Token Index: 996

Text #8

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1580425 (Python Code)

Max Activating Token Index: 50

Text #9

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.0934. Min Act: -0.0001

Data Index: 1502213 (Python Code)

Max Activating Token Index: 34

Text #10

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1581596 (Python Code)

Max Activating Token Index: 160

Text #11

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.0986. Min Act: -0.0001

Data Index: 1472384 (Python Code)

Max Activating Token Index: 17

Text #12

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.0950. Min Act: -0.0001

Data Index: 1387755 (Python Code)

Max Activating Token Index: 895

Text #13

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.0978. Min Act: -0.0001

Data Index: 1385213 (Python Code)

Max Activating Token Index: 178

Text #14

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.0884. Min Act: -0.0001

Data Index: 1477538 (Python Code)

Max Activating Token Index: 91

Text #15

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.0882. Min Act: -0.0001

Data Index: 1402104 (Python Code)

Max Activating Token Index: 723

Text #16

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1656410 (Python Code)

Max Activating Token Index: 879

Text #17

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1414299 (Python Code)

Max Activating Token Index: 547

Text #18

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1606486 (Python Code)

Max Activating Token Index: 589

Text #19

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1483977 (Python Code)

Max Activating Token Index: 713