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

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

Neuron 5863 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3642. Min Act: -0.0000

Data Index: 1622764 (Python Code)

Max Activating Token Index: 329

Text #1

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1522075 (Python Code)

Max Activating Token Index: 437

Text #2

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1596356 (Python Code)

Max Activating Token Index: 673

Text #3

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.4023. Min Act: -0.0001

Data Index: 1535652 (Python Code)

Max Activating Token Index: 1001

Text #4

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3671. Min Act: -0.0001

Data Index: 1408886 (Python Code)

Max Activating Token Index: 133

Text #5

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3549. Min Act: -0.0001

Data Index: 1425554 (Python Code)

Max Activating Token Index: 511

Text #6

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3599. Min Act: -0.0000

Data Index: 1369489 (Python Code)

Max Activating Token Index: 1011

Text #7

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3558. Min Act: -0.0001

Data Index: 1512858 (Python Code)

Max Activating Token Index: 629

Text #8

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1608716 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1556027 (Python Code)

Max Activating Token Index: 676

Text #10

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1497315 (Python Code)

Max Activating Token Index: 84

Text #11

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1524067 (Python Code)

Max Activating Token Index: 175

Text #12

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1571554 (Python Code)

Max Activating Token Index: 968

Text #13

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3367. Min Act: -0.0001

Data Index: 1409110 (Python Code)

Max Activating Token Index: 272

Text #14

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3109. Min Act: -0.0001

Data Index: 1403380 (Python Code)

Max Activating Token Index: 330

Text #15

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1514664 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1528825 (Python Code)

Max Activating Token Index: 382

Text #17

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3268. Min Act: -0.0001

Data Index: 1429027 (Python Code)

Max Activating Token Index: 704

Text #18

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1491597 (Python Code)

Max Activating Token Index: 547

Text #19

Max Range: 0.4034. Min Range: -0.4034

Max Act: 0.3204. Min Act: -0.0000

Data Index: 1516205 (Python Code)

Max Activating Token Index: 595