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

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

Neuron 4623 in Layer 1

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: 0.1093. Min Range: -0.1093

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1486328 (Python Code)

Max Activating Token Index: 139

Text #1

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1490875 (Python Code)

Max Activating Token Index: 342

Text #2

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1023. Min Act: -0.0002

Data Index: 1586460 (Python Code)

Max Activating Token Index: 253

Text #3

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1012. Min Act: -0.0002

Data Index: 1362995 (Python Code)

Max Activating Token Index: 337

Text #4

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1426281 (Python Code)

Max Activating Token Index: 54

Text #5

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.1019. Min Act: -0.0002

Data Index: 1435194 (Python Code)

Max Activating Token Index: 605

Text #6

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1603969 (Python Code)

Max Activating Token Index: 794

Text #7

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1407422 (Python Code)

Max Activating Token Index: 345

Text #8

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0997. Min Act: -0.0002

Data Index: 1626288 (Python Code)

Max Activating Token Index: 820

Text #9

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0985. Min Act: -0.0002

Data Index: 1412637 (Python Code)

Max Activating Token Index: 736

Text #10

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0967. Min Act: -0.0002

Data Index: 1555506 (Python Code)

Max Activating Token Index: 81

Text #11

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1395596 (Python Code)

Max Activating Token Index: 276

Text #12

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1499918 (Python Code)

Max Activating Token Index: 222

Text #13

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1637790 (Python Code)

Max Activating Token Index: 270

Text #14

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1430573 (Python Code)

Max Activating Token Index: 353

Text #15

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1421854 (Python Code)

Max Activating Token Index: 478

Text #16

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1364502 (Python Code)

Max Activating Token Index: 174

Text #17

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1369000 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0937. Min Act: -0.0002

Data Index: 1417810 (Python Code)

Max Activating Token Index: 129

Text #19

Max Range: 0.1093. Min Range: -0.1093

Max Act: 0.0959. Min Act: -0.0002

Data Index: 1475306 (Python Code)

Max Activating Token Index: 572