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

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

Neuron 2782 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1389833 (Python Code)

Max Activating Token Index: 754

Text #1

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.8118. Min Act: -0.0000

Data Index: 1562472 (Python Code)

Max Activating Token Index: 228

Text #2

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.7751. Min Act: -0.0000

Data Index: 1558937 (Python Code)

Max Activating Token Index: 775

Text #3

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.7337. Min Act: -0.0000

Data Index: 1547233 (Python Code)

Max Activating Token Index: 376

Text #4

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1523214 (Python Code)

Max Activating Token Index: 741

Text #5

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1427178 (Python Code)

Max Activating Token Index: 848

Text #6

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1443648 (Python Code)

Max Activating Token Index: 810

Text #7

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1419810 (Python Code)

Max Activating Token Index: 44

Text #8

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1574521 (Python Code)

Max Activating Token Index: 849

Text #9

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1623681 (Python Code)

Max Activating Token Index: 30

Text #10

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.6134. Min Act: -0.0000

Data Index: 1424383 (Python Code)

Max Activating Token Index: 338

Text #11

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1636956 (Python Code)

Max Activating Token Index: 980

Text #12

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1606477 (Python Code)

Max Activating Token Index: 345

Text #13

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1630975 (Python Code)

Max Activating Token Index: 330

Text #14

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1491510 (Python Code)

Max Activating Token Index: 408

Text #15

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1428696 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.5696. Min Act: -0.0000

Data Index: 1394748 (Python Code)

Max Activating Token Index: 238

Text #17

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.5717. Min Act: -0.0000

Data Index: 1506551 (Python Code)

Max Activating Token Index: 916

Text #18

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1643111 (Python Code)

Max Activating Token Index: 373

Text #19

Max Range: 0.8253. Min Range: -0.8253

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1434518 (Python Code)

Max Activating Token Index: 192