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

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

Neuron 5814 in Layer 0

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: 0.1267. Min Range: -0.1267

Max Act: 0.1267. Min Act: -0.0001

Data Index: 1565077 (Python Code)

Max Activating Token Index: 324

Text #1

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1417969 (Python Code)

Max Activating Token Index: 598

Text #2

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1601099 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0889. Min Act: -0.0001

Data Index: 1451254 (Python Code)

Max Activating Token Index: 475

Text #4

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1525718 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1535904 (Python Code)

Max Activating Token Index: 945

Text #6

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1587291 (Python Code)

Max Activating Token Index: 16

Text #7

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0830. Min Act: -0.0001

Data Index: 1420941 (Python Code)

Max Activating Token Index: 568

Text #8

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0793. Min Act: -0.0001

Data Index: 1447311 (Python Code)

Max Activating Token Index: 610

Text #9

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1371975 (Python Code)

Max Activating Token Index: 98

Text #10

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0743. Min Act: -0.0001

Data Index: 1653160 (Python Code)

Max Activating Token Index: 337

Text #11

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1445441 (Python Code)

Max Activating Token Index: 80

Text #12

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0720. Min Act: -0.0001

Data Index: 1371096 (Python Code)

Max Activating Token Index: 57

Text #13

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1407841 (Python Code)

Max Activating Token Index: 81

Text #14

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0697. Min Act: -0.0001

Data Index: 1650428 (Python Code)

Max Activating Token Index: 379

Text #15

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1435630 (Python Code)

Max Activating Token Index: 424

Text #16

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0679. Min Act: -0.0001

Data Index: 1630375 (Python Code)

Max Activating Token Index: 374

Text #17

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1416652 (Python Code)

Max Activating Token Index: 716

Text #18

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0688. Min Act: -0.0000

Data Index: 1548517 (Python Code)

Max Activating Token Index: 40

Text #19

Max Range: 0.1267. Min Range: -0.1267

Max Act: 0.0681. Min Act: -0.0000

Data Index: 1496551 (Python Code)

Max Activating Token Index: 26