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

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

Neuron 4810 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: 0.0624. Min Range: -0.0624

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1402728 (Python Code)

Max Activating Token Index: 187

Text #1

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1493481 (Python Code)

Max Activating Token Index: 269

Text #2

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1586099 (Python Code)

Max Activating Token Index: 214

Text #3

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1571249 (Python Code)

Max Activating Token Index: 587

Text #4

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1404756 (Python Code)

Max Activating Token Index: 975

Text #5

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1581500 (Python Code)

Max Activating Token Index: 239

Text #6

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1480428 (Python Code)

Max Activating Token Index: 904

Text #7

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1591080 (Python Code)

Max Activating Token Index: 137

Text #8

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1538697 (Python Code)

Max Activating Token Index: 297

Text #9

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1420907 (Python Code)

Max Activating Token Index: 758

Text #10

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1511711 (Python Code)

Max Activating Token Index: 592

Text #11

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1360727 (Python Code)

Max Activating Token Index: 633

Text #12

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1417682 (Python Code)

Max Activating Token Index: 17

Text #13

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0518. Min Act: -0.0002

Data Index: 1367747 (Python Code)

Max Activating Token Index: 890

Text #14

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1457180 (Python Code)

Max Activating Token Index: 962

Text #15

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1529709 (Python Code)

Max Activating Token Index: 94

Text #16

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1559744 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1627209 (Python Code)

Max Activating Token Index: 235

Text #18

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1653818 (Python Code)

Max Activating Token Index: 295

Text #19

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1528967 (Python Code)

Max Activating Token Index: 246