Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 266 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0823. Min Act: -0.0003

Data Index: 1405661 (Python Code)

Max Activating Token Index: 971

Text #1

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0803. Min Act: -0.0003

Data Index: 1649487 (Python Code)

Max Activating Token Index: 868

Text #2

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0737. Min Act: -0.0003

Data Index: 1483411 (Python Code)

Max Activating Token Index: 817

Text #3

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0716. Min Act: -0.0003

Data Index: 1581431 (Python Code)

Max Activating Token Index: 482

Text #4

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0714. Min Act: -0.0003

Data Index: 1541900 (Python Code)

Max Activating Token Index: 475

Text #5

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0702. Min Act: -0.0003

Data Index: 1365828 (Python Code)

Max Activating Token Index: 905

Text #6

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0673. Min Act: -0.0003

Data Index: 1495000 (Python Code)

Max Activating Token Index: 229

Text #7

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0669. Min Act: -0.0003

Data Index: 1470384 (Python Code)

Max Activating Token Index: 291

Text #8

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1544634 (Python Code)

Max Activating Token Index: 13

Text #9

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1456697 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1592253 (Python Code)

Max Activating Token Index: 230

Text #11

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0676. Min Act: -0.0003

Data Index: 1654363 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0659. Min Act: -0.0003

Data Index: 1620062 (Python Code)

Max Activating Token Index: 373

Text #13

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0656. Min Act: -0.0003

Data Index: 1571327 (Python Code)

Max Activating Token Index: 567

Text #14

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1390840 (Python Code)

Max Activating Token Index: 20

Text #15

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0663. Min Act: -0.0003

Data Index: 1517974 (Python Code)

Max Activating Token Index: 589

Text #16

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1529986 (Python Code)

Max Activating Token Index: 937

Text #17

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1377136 (Python Code)

Max Activating Token Index: 388

Text #18

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0652. Min Act: -0.0003

Data Index: 1360480 (Python Code)

Max Activating Token Index: 734

Text #19

Max Range: 0.0823. Min Range: -0.0823

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1383662 (Python Code)

Max Activating Token Index: 738