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

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

Neuron 4417 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.2107. Min Act: -0.0000

Data Index: 1495095 (Python Code)

Max Activating Token Index: 257

Text #1

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.2076. Min Act: 0.0001

Data Index: 1507299 (Python Code)

Max Activating Token Index: 67

Text #2

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.2057. Min Act: 0.0000

Data Index: 1369113 (Python Code)

Max Activating Token Index: 915

Text #3

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1303905 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1938. Min Act: 0.0000

Data Index: 1582076 (Python Code)

Max Activating Token Index: 384

Text #5

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1927. Min Act: 0.0000

Data Index: 1455714 (Python Code)

Max Activating Token Index: 108

Text #6

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1471509 (Python Code)

Max Activating Token Index: 826

Text #7

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1814. Min Act: 0.0002

Data Index: 1506755 (Python Code)

Max Activating Token Index: 983

Text #8

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1811. Min Act: 0.0002

Data Index: 1570839 (Python Code)

Max Activating Token Index: 547

Text #9

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1685. Min Act: 0.0001

Data Index: 1615969 (Python Code)

Max Activating Token Index: 338

Text #10

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1769. Min Act: 0.0001

Data Index: 1438664 (Python Code)

Max Activating Token Index: 135

Text #11

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1676. Min Act: 0.0001

Data Index: 1426115 (Python Code)

Max Activating Token Index: 122

Text #12

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1595. Min Act: 0.0001

Data Index: 1392476 (Python Code)

Max Activating Token Index: 183

Text #13

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1686. Min Act: 0.0000

Data Index: 1390945 (Python Code)

Max Activating Token Index: 150

Text #14

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1611. Min Act: 0.0000

Data Index: 1620718 (Python Code)

Max Activating Token Index: 631

Text #15

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1656. Min Act: 0.0000

Data Index: 1553291 (Python Code)

Max Activating Token Index: 275

Text #16

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1594. Min Act: 0.0000

Data Index: 1446164 (Python Code)

Max Activating Token Index: 609

Text #17

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1603. Min Act: 0.0001

Data Index: 1531872 (Python Code)

Max Activating Token Index: 930

Text #18

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1375261 (Python Code)

Max Activating Token Index: 923

Text #19

Max Range: 0.2107. Min Range: -0.2107

Max Act: 0.1665. Min Act: -0.0000

Data Index: 1475774 (Python Code)

Max Activating Token Index: 929