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

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

Neuron 6105 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.2005. Min Act: -0.0002

Data Index: 1349019 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1920. Min Act: -0.0002

Data Index: 983406 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1818. Min Act: -0.0002

Data Index: 610084 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1870. Min Act: -0.0002

Data Index: 1344507 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1796. Min Act: -0.0002

Data Index: 1300315 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1735. Min Act: -0.0002

Data Index: 508265 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1660. Min Act: -0.0002

Data Index: 1589707 (Python Code)

Max Activating Token Index: 968

Text #7

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1613. Min Act: -0.0002

Data Index: 1309089 (C4 (Web Text))

Max Activating Token Index: 660

Text #8

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1655. Min Act: -0.0002

Data Index: 716910 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1664. Min Act: -0.0002

Data Index: 1233608 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1668. Min Act: -0.0002

Data Index: 1513131 (Python Code)

Max Activating Token Index: 554

Text #11

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1584. Min Act: -0.0002

Data Index: 884197 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1560. Min Act: -0.0002

Data Index: 160455 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1569. Min Act: -0.0002

Data Index: 238197 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1556. Min Act: -0.0002

Data Index: 441183 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1504. Min Act: -0.0002

Data Index: 1545038 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1499. Min Act: -0.0002

Data Index: 1227215 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1500. Min Act: -0.0002

Data Index: 202633 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1553. Min Act: -0.0002

Data Index: 681644 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 0.2005. Min Range: -0.2005

Max Act: 0.1473. Min Act: -0.0002

Data Index: 393844 (C4 (Web Text))

Max Activating Token Index: 297