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

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

Neuron 5296 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: 0.0632. Min Range: -0.0632

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1510520 (Python Code)

Max Activating Token Index: 69

Text #1

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1568375 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0616. Min Act: -0.0002

Data Index: 1638843 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1570958 (Python Code)

Max Activating Token Index: 241

Text #4

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1544028 (Python Code)

Max Activating Token Index: 444

Text #5

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1615358 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0597. Min Act: -0.0001

Data Index: 1411730 (Python Code)

Max Activating Token Index: 886

Text #7

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1528812 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1395790 (Python Code)

Max Activating Token Index: 995

Text #9

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1361327 (Python Code)

Max Activating Token Index: 599

Text #10

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0585. Min Act: -0.0001

Data Index: 1475722 (Python Code)

Max Activating Token Index: 993

Text #11

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0590. Min Act: -0.0002

Data Index: 1418503 (Python Code)

Max Activating Token Index: 93

Text #12

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1408966 (Python Code)

Max Activating Token Index: 23

Text #13

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1637992 (Python Code)

Max Activating Token Index: 120

Text #14

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1364581 (Python Code)

Max Activating Token Index: 249

Text #15

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1397789 (Python Code)

Max Activating Token Index: 73

Text #16

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1437607 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1388997 (Python Code)

Max Activating Token Index: 523

Text #18

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1461312 (Python Code)

Max Activating Token Index: 166

Text #19

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0585. Min Act: -0.0001

Data Index: 1398622 (Python Code)

Max Activating Token Index: 3