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

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

Neuron 1772 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: 0.0818. Min Range: -0.0818

Max Act: 0.0818. Min Act: -0.0002

Data Index: 1449792 (Python Code)

Max Activating Token Index: 468

Text #1

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1470812 (Python Code)

Max Activating Token Index: 65

Text #2

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1526667 (Python Code)

Max Activating Token Index: 142

Text #3

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0700. Min Act: -0.0002

Data Index: 212254 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1612109 (Python Code)

Max Activating Token Index: 291

Text #5

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0692. Min Act: -0.0002

Data Index: 332913 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0657. Min Act: -0.0002

Data Index: 1438442 (Python Code)

Max Activating Token Index: 937

Text #7

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1489791 (Python Code)

Max Activating Token Index: 446

Text #8

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1654981 (Python Code)

Max Activating Token Index: 335

Text #9

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0655. Min Act: -0.0002

Data Index: 310676 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1650472 (Python Code)

Max Activating Token Index: 483

Text #11

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0647. Min Act: -0.0002

Data Index: 1408606 (Python Code)

Max Activating Token Index: 852

Text #12

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1426403 (Python Code)

Max Activating Token Index: 1019

Text #13

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1395988 (Python Code)

Max Activating Token Index: 525

Text #14

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0620. Min Act: -0.0002

Data Index: 948681 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1518843 (Python Code)

Max Activating Token Index: 705

Text #16

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1472404 (Python Code)

Max Activating Token Index: 606

Text #17

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1580034 (Python Code)

Max Activating Token Index: 397

Text #18

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1384296 (Python Code)

Max Activating Token Index: 584

Text #19

Max Range: 0.0818. Min Range: -0.0818

Max Act: 0.0612. Min Act: -0.0002

Data Index: 289322 (C4 (Web Text))

Max Activating Token Index: 396