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

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

Neuron 985 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: 0.0709. Min Range: -0.0709

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1545696 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1495278 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1610647 (Python Code)

Max Activating Token Index: 645

Text #3

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1393772 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1610192 (Python Code)

Max Activating Token Index: 664

Text #5

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1555678 (Python Code)

Max Activating Token Index: 852

Text #6

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1639502 (Python Code)

Max Activating Token Index: 83

Text #7

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0627. Min Act: -0.0002

Data Index: 1517449 (Python Code)

Max Activating Token Index: 927

Text #8

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1581909 (Python Code)

Max Activating Token Index: 99

Text #9

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1445966 (Python Code)

Max Activating Token Index: 133

Text #10

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0635. Min Act: -0.0001

Data Index: 1383437 (Python Code)

Max Activating Token Index: 42

Text #11

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0625. Min Act: -0.0001

Data Index: 1386699 (Python Code)

Max Activating Token Index: 57

Text #12

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0633. Min Act: -0.0001

Data Index: 1446748 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0622. Min Act: -0.0001

Data Index: 1646752 (Python Code)

Max Activating Token Index: 444

Text #14

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0637. Min Act: -0.0001

Data Index: 1464475 (Python Code)

Max Activating Token Index: 239

Text #15

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1524437 (Python Code)

Max Activating Token Index: 57

Text #16

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1373453 (Python Code)

Max Activating Token Index: 163

Text #17

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1551263 (Python Code)

Max Activating Token Index: 61

Text #18

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1506245 (Python Code)

Max Activating Token Index: 871

Text #19

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1601555 (Python Code)

Max Activating Token Index: 97