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

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

Neuron 5927 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: 0.0670. Min Range: -0.0670

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1624368 (Python Code)

Max Activating Token Index: 41

Text #1

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1369114 (Python Code)

Max Activating Token Index: 190

Text #2

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1407443 (Python Code)

Max Activating Token Index: 70

Text #3

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0652. Min Act: -0.0001

Data Index: 1453851 (Python Code)

Max Activating Token Index: 306

Text #4

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1378386 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1543469 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1537299 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1579259 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1411314 (Python Code)

Max Activating Token Index: 3

Text #9

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1609145 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1562807 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1622599 (Python Code)

Max Activating Token Index: 3

Text #12

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1411808 (Python Code)

Max Activating Token Index: 3

Text #13

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1417725 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1651202 (Python Code)

Max Activating Token Index: 137

Text #15

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1545014 (Python Code)

Max Activating Token Index: 228

Text #16

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1428541 (Python Code)

Max Activating Token Index: 19

Text #17

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0629. Min Act: -0.0001

Data Index: 1564164 (Python Code)

Max Activating Token Index: 25

Text #18

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0624. Min Act: -0.0001

Data Index: 1535515 (Python Code)

Max Activating Token Index: 482

Text #19

Max Range: 0.0670. Min Range: -0.0670

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1557864 (Python Code)

Max Activating Token Index: 222