Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1056 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3835. Min Act: -0.0001

Data Index: 1482333 (Python Code)

Max Activating Token Index: 747

Text #1

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3691. Min Act: -0.0001

Data Index: 1466573 (Python Code)

Max Activating Token Index: 37

Text #2

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3859. Min Act: -0.0001

Data Index: 1442568 (Python Code)

Max Activating Token Index: 453

Text #3

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3476. Min Act: -0.0001

Data Index: 1475924 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3025. Min Act: -0.0001

Data Index: 1467142 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3624. Min Act: -0.0001

Data Index: 1452939 (Python Code)

Max Activating Token Index: 719

Text #6

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3468. Min Act: -0.0001

Data Index: 1570766 (Python Code)

Max Activating Token Index: 215

Text #7

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3075. Min Act: -0.0001

Data Index: 1545897 (Python Code)

Max Activating Token Index: 34

Text #8

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2663. Min Act: -0.0001

Data Index: 1516448 (Python Code)

Max Activating Token Index: 598

Text #9

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3326. Min Act: -0.0001

Data Index: 1608802 (Python Code)

Max Activating Token Index: 357

Text #10

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3407. Min Act: -0.0001

Data Index: 1622573 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3162. Min Act: -0.0001

Data Index: 1588666 (Python Code)

Max Activating Token Index: 598

Text #12

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3220. Min Act: -0.0001

Data Index: 1423314 (Python Code)

Max Activating Token Index: 753

Text #13

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3039. Min Act: -0.0001

Data Index: 1473018 (Python Code)

Max Activating Token Index: 307

Text #14

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3080. Min Act: -0.0001

Data Index: 1595095 (Python Code)

Max Activating Token Index: 30

Text #15

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.3030. Min Act: -0.0001

Data Index: 1411874 (Python Code)

Max Activating Token Index: 76

Text #16

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2811. Min Act: -0.0001

Data Index: 1622571 (Python Code)

Max Activating Token Index: 416

Text #17

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2718. Min Act: -0.0001

Data Index: 1542339 (Python Code)

Max Activating Token Index: 241

Text #18

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2660. Min Act: -0.0001

Data Index: 1555016 (Python Code)

Max Activating Token Index: 167

Text #19

Max Range: 0.3859. Min Range: -0.3859

Max Act: 0.2922. Min Act: -0.0001

Data Index: 1500898 (Python Code)

Max Activating Token Index: 131