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

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

Neuron 6016 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: 1.9681. Min Range: -1.9681

Max Act: 1.9640. Min Act: -0.0002

Data Index: 1452980 (Python Code)

Max Activating Token Index: 830

Text #1

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.9681. Min Act: -0.0002

Data Index: 1519778 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.9661. Min Act: -0.0002

Data Index: 1574385 (Python Code)

Max Activating Token Index: 31

Text #3

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8140. Min Act: -0.0002

Data Index: 1639150 (Python Code)

Max Activating Token Index: 875

Text #4

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.7867. Min Act: -0.0002

Data Index: 1386591 (Python Code)

Max Activating Token Index: 479

Text #5

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8624. Min Act: -0.0002

Data Index: 1558603 (Python Code)

Max Activating Token Index: 900

Text #6

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.8755. Min Act: -0.0002

Data Index: 1468236 (Python Code)

Max Activating Token Index: 590

Text #7

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.7718. Min Act: -0.0002

Data Index: 1595725 (Python Code)

Max Activating Token Index: 879

Text #8

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.7971. Min Act: -0.0002

Data Index: 1554811 (Python Code)

Max Activating Token Index: 756

Text #9

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.7484. Min Act: -0.0002

Data Index: 1476225 (Python Code)

Max Activating Token Index: 48

Text #10

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.7730. Min Act: -0.0002

Data Index: 1535003 (Python Code)

Max Activating Token Index: 566

Text #11

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.7713. Min Act: -0.0002

Data Index: 1524961 (Python Code)

Max Activating Token Index: 797

Text #12

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.7415. Min Act: -0.0002

Data Index: 1369944 (Python Code)

Max Activating Token Index: 380

Text #13

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.7536. Min Act: -0.0002

Data Index: 1520194 (Python Code)

Max Activating Token Index: 73

Text #14

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.7649. Min Act: -0.0002

Data Index: 1616333 (Python Code)

Max Activating Token Index: 552

Text #15

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.7677. Min Act: -0.0002

Data Index: 1434319 (Python Code)

Max Activating Token Index: 915

Text #16

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.7764. Min Act: -0.0002

Data Index: 1470235 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.7186. Min Act: -0.0002

Data Index: 1481203 (Python Code)

Max Activating Token Index: 374

Text #18

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.7506. Min Act: -0.0002

Data Index: 1554172 (Python Code)

Max Activating Token Index: 946

Text #19

Max Range: 1.9681. Min Range: -1.9681

Max Act: 1.7680. Min Act: -0.0002

Data Index: 1519599 (Python Code)

Max Activating Token Index: 416