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

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

Neuron 5018 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: 0.7312. Min Range: -0.7312

Max Act: 0.7312. Min Act: -0.0001

Data Index: 1512357 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.7300. Min Act: -0.0001

Data Index: 1381315 (Python Code)

Max Activating Token Index: 5

Text #2

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.7250. Min Act: -0.0001

Data Index: 1378112 (Python Code)

Max Activating Token Index: 560

Text #3

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.7044. Min Act: -0.0001

Data Index: 1523018 (Python Code)

Max Activating Token Index: 22

Text #4

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6915. Min Act: -0.0001

Data Index: 1564670 (Python Code)

Max Activating Token Index: 823

Text #5

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6986. Min Act: -0.0001

Data Index: 1584063 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6701. Min Act: -0.0001

Data Index: 1449506 (Python Code)

Max Activating Token Index: 424

Text #7

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6827. Min Act: -0.0001

Data Index: 1466941 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6687. Min Act: -0.0001

Data Index: 1433658 (Python Code)

Max Activating Token Index: 405

Text #9

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6702. Min Act: -0.0001

Data Index: 1372375 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6644. Min Act: -0.0001

Data Index: 1443386 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6800. Min Act: -0.0001

Data Index: 906147 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6683. Min Act: -0.0001

Data Index: 1431023 (Python Code)

Max Activating Token Index: 7

Text #13

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6599. Min Act: -0.0001

Data Index: 1582129 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6682. Min Act: -0.0002

Data Index: 1380805 (Python Code)

Max Activating Token Index: 448

Text #15

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6683. Min Act: -0.0001

Data Index: 1386754 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6502. Min Act: -0.0001

Data Index: 1471457 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6589. Min Act: -0.0001

Data Index: 1630425 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6620. Min Act: -0.0001

Data Index: 1473930 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 0.7312. Min Range: -0.7312

Max Act: 0.6506. Min Act: -0.0001

Data Index: 1505282 (Python Code)

Max Activating Token Index: 9