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

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

Neuron 3991 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.7677. Min Act: -0.0000

Data Index: 1462712 (Python Code)

Max Activating Token Index: 505

Text #1

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.6836. Min Act: -0.0000

Data Index: 1521095 (Python Code)

Max Activating Token Index: 61

Text #2

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.6721. Min Act: -0.0000

Data Index: 1380565 (Python Code)

Max Activating Token Index: 150

Text #3

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.4337. Min Act: -0.0000

Data Index: 1382074 (Python Code)

Max Activating Token Index: 214

Text #4

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.8824. Min Act: -0.0000

Data Index: 1383438 (Python Code)

Max Activating Token Index: 1016

Text #5

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.4041. Min Act: -0.0000

Data Index: 1577539 (Python Code)

Max Activating Token Index: 365

Text #6

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.4698. Min Act: -0.0000

Data Index: 1530634 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.2683. Min Act: -0.0000

Data Index: 1608133 (Python Code)

Max Activating Token Index: 671

Text #8

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.3657. Min Act: -0.0000

Data Index: 1606542 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.1129. Min Act: -0.0000

Data Index: 1514349 (Python Code)

Max Activating Token Index: 333

Text #10

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.3566. Min Act: -0.0000

Data Index: 1394628 (Python Code)

Max Activating Token Index: 797

Text #11

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.2048. Min Act: -0.0000

Data Index: 1469736 (Python Code)

Max Activating Token Index: 230

Text #12

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.0878. Min Act: -0.0000

Data Index: 1636329 (Python Code)

Max Activating Token Index: 224

Text #13

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.2276. Min Act: -0.0000

Data Index: 1460986 (Python Code)

Max Activating Token Index: 26

Text #14

Max Range: 3.8824. Min Range: -3.8824

Max Act: 2.7383. Min Act: -0.0000

Data Index: 1495650 (Python Code)

Max Activating Token Index: 105

Text #15

Max Range: 3.8824. Min Range: -3.8824

Max Act: 3.0237. Min Act: -0.0000

Data Index: 1553333 (Python Code)

Max Activating Token Index: 1011

Text #16

Max Range: 3.8824. Min Range: -3.8824

Max Act: 2.8438. Min Act: -0.0000

Data Index: 1405442 (Python Code)

Max Activating Token Index: 842

Text #17

Max Range: 3.8824. Min Range: -3.8824

Max Act: 2.8020. Min Act: -0.0000

Data Index: 1593467 (Python Code)

Max Activating Token Index: 822

Text #18

Max Range: 3.8824. Min Range: -3.8824

Max Act: 2.9345. Min Act: -0.0000

Data Index: 1557753 (Python Code)

Max Activating Token Index: 821

Text #19

Max Range: 3.8824. Min Range: -3.8824

Max Act: 2.8967. Min Act: -0.0000

Data Index: 1481216 (Python Code)

Max Activating Token Index: 824