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

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

Neuron 4262 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: 1.0608. Min Range: -1.0608

Max Act: 1.0608. Min Act: -0.0002

Data Index: 1468936 (Python Code)

Max Activating Token Index: 25

Text #1

Max Range: 1.0608. Min Range: -1.0608

Max Act: 1.0509. Min Act: -0.0002

Data Index: 1422149 (Python Code)

Max Activating Token Index: 35

Text #2

Max Range: 1.0608. Min Range: -1.0608

Max Act: 1.0234. Min Act: -0.0002

Data Index: 1393307 (Python Code)

Max Activating Token Index: 34

Text #3

Max Range: 1.0608. Min Range: -1.0608

Max Act: 1.0197. Min Act: -0.0002

Data Index: 1442480 (Python Code)

Max Activating Token Index: 590

Text #4

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9877. Min Act: -0.0002

Data Index: 1428650 (Python Code)

Max Activating Token Index: 117

Text #5

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9972. Min Act: -0.0002

Data Index: 1569611 (Python Code)

Max Activating Token Index: 106

Text #6

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9875. Min Act: -0.0002

Data Index: 1474849 (Python Code)

Max Activating Token Index: 35

Text #7

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9973. Min Act: -0.0002

Data Index: 1369663 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9728. Min Act: -0.0002

Data Index: 1559792 (Python Code)

Max Activating Token Index: 803

Text #9

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9738. Min Act: -0.0002

Data Index: 1430722 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9754. Min Act: -0.0002

Data Index: 1493744 (Python Code)

Max Activating Token Index: 80

Text #11

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9625. Min Act: -0.0002

Data Index: 1496186 (Python Code)

Max Activating Token Index: 214

Text #12

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9560. Min Act: -0.0002

Data Index: 1543886 (Python Code)

Max Activating Token Index: 500

Text #13

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9797. Min Act: -0.0002

Data Index: 1650973 (Python Code)

Max Activating Token Index: 114

Text #14

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9536. Min Act: -0.0002

Data Index: 1523332 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9637. Min Act: -0.0002

Data Index: 1541811 (Python Code)

Max Activating Token Index: 72

Text #16

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9680. Min Act: -0.0002

Data Index: 1646595 (Python Code)

Max Activating Token Index: 78

Text #17

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9350. Min Act: -0.0002

Data Index: 1521904 (Python Code)

Max Activating Token Index: 52

Text #18

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9418. Min Act: -0.0002

Data Index: 1400954 (Python Code)

Max Activating Token Index: 35

Text #19

Max Range: 1.0608. Min Range: -1.0608

Max Act: 0.9393. Min Act: -0.0002

Data Index: 1391333 (Python Code)

Max Activating Token Index: 14