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

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

Neuron 5499 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: 0.7581. Min Range: -0.7581

Max Act: 0.7581. Min Act: -0.0002

Data Index: 1540640 (Python Code)

Max Activating Token Index: 79

Text #1

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6865. Min Act: -0.0002

Data Index: 1597719 (Python Code)

Max Activating Token Index: 780

Text #2

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6969. Min Act: -0.0002

Data Index: 1393389 (Python Code)

Max Activating Token Index: 162

Text #3

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6553. Min Act: -0.0002

Data Index: 1485606 (Python Code)

Max Activating Token Index: 191

Text #4

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6601. Min Act: -0.0002

Data Index: 1543688 (Python Code)

Max Activating Token Index: 833

Text #5

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6276. Min Act: -0.0002

Data Index: 1405022 (Python Code)

Max Activating Token Index: 1004

Text #6

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6275. Min Act: -0.0002

Data Index: 1555924 (Python Code)

Max Activating Token Index: 821

Text #7

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6145. Min Act: -0.0002

Data Index: 1622503 (Python Code)

Max Activating Token Index: 101

Text #8

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6231. Min Act: -0.0002

Data Index: 1362217 (Python Code)

Max Activating Token Index: 426

Text #9

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6278. Min Act: -0.0002

Data Index: 1473086 (Python Code)

Max Activating Token Index: 603

Text #10

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6404. Min Act: -0.0002

Data Index: 1511234 (Python Code)

Max Activating Token Index: 626

Text #11

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6116. Min Act: -0.0002

Data Index: 1551194 (Python Code)

Max Activating Token Index: 438

Text #12

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5995. Min Act: -0.0002

Data Index: 1573475 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5990. Min Act: -0.0002

Data Index: 1540006 (Python Code)

Max Activating Token Index: 650

Text #14

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6070. Min Act: -0.0002

Data Index: 1558423 (Python Code)

Max Activating Token Index: 122

Text #15

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5963. Min Act: -0.0002

Data Index: 1478724 (Python Code)

Max Activating Token Index: 231

Text #16

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.5951. Min Act: -0.0002

Data Index: 1509732 (Python Code)

Max Activating Token Index: 434

Text #17

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6014. Min Act: -0.0002

Data Index: 1374513 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6027. Min Act: -0.0002

Data Index: 1470071 (Python Code)

Max Activating Token Index: 398

Text #19

Max Range: 0.7581. Min Range: -0.7581

Max Act: 0.6034. Min Act: -0.0002

Data Index: 1624761 (Python Code)

Max Activating Token Index: 828