Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2395 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1921. Min Act: -0.0001

Data Index: 1316851 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1916. Min Act: 0.0001

Data Index: 1314427 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1873. Min Act: -0.0001

Data Index: 547099 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1842. Min Act: -0.0001

Data Index: 105190 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1830. Min Act: -0.0001

Data Index: 521739 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1790. Min Act: -0.0001

Data Index: 1267712 (C4 (Web Text))

Max Activating Token Index: 51

Text #6

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1727. Min Act: -0.0001

Data Index: 845669 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1740. Min Act: 0.0001

Data Index: 646317 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1813. Min Act: -0.0001

Data Index: 479070 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1697. Min Act: -0.0000

Data Index: 704215 (C4 (Web Text))

Max Activating Token Index: 814

Text #10

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1781. Min Act: -0.0001

Data Index: 1173760 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1660. Min Act: -0.0000

Data Index: 1036805 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1712. Min Act: 0.0001

Data Index: 569520 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1615. Min Act: -0.0001

Data Index: 850489 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1613. Min Act: -0.0001

Data Index: 392178 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1578. Min Act: -0.0001

Data Index: 1132051 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1602. Min Act: -0.0001

Data Index: 262078 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1586. Min Act: -0.0001

Data Index: 420470 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1592. Min Act: -0.0001

Data Index: 1281675 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1571. Min Act: -0.0001

Data Index: 812660 (C4 (Web Text))

Max Activating Token Index: 813