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

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

Neuron 4752 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.0887. Min Act: -0.0000

Data Index: 1518711 (Python Code)

Max Activating Token Index: 584

Text #1

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.2237. Min Act: -0.0000

Data Index: 1563903 (Python Code)

Max Activating Token Index: 271

Text #2

Max Range: 3.2237. Min Range: -3.2237

Max Act: 2.9164. Min Act: -0.0000

Data Index: 1575800 (Python Code)

Max Activating Token Index: 909

Text #3

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1994. Min Act: -0.0000

Data Index: 1468960 (Python Code)

Max Activating Token Index: 253

Text #4

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1991. Min Act: -0.0000

Data Index: 1483078 (Python Code)

Max Activating Token Index: 482

Text #5

Max Range: 3.2237. Min Range: -3.2237

Max Act: 2.8630. Min Act: -0.0000

Data Index: 1443885 (Python Code)

Max Activating Token Index: 640

Text #6

Max Range: 3.2237. Min Range: -3.2237

Max Act: 3.1029. Min Act: -0.0000

Data Index: 1537668 (Python Code)

Max Activating Token Index: 468

Text #7

Max Range: 3.2237. Min Range: -3.2237

Max Act: 2.9255. Min Act: -0.0000

Data Index: 1523797 (Python Code)

Max Activating Token Index: 504

Text #8

Max Range: 3.2237. Min Range: -3.2237

Max Act: 2.9099. Min Act: -0.0000

Data Index: 1482632 (Python Code)

Max Activating Token Index: 20

Text #9

Max Range: 3.2237. Min Range: -3.2237

Max Act: 2.7853. Min Act: -0.0000

Data Index: 1398052 (Python Code)

Max Activating Token Index: 791

Text #10

Max Range: 3.2237. Min Range: -3.2237

Max Act: 2.8981. Min Act: -0.0000

Data Index: 1472919 (Python Code)

Max Activating Token Index: 489

Text #11

Max Range: 3.2237. Min Range: -3.2237

Max Act: 2.7612. Min Act: -0.0000

Data Index: 1518156 (Python Code)

Max Activating Token Index: 32

Text #12

Max Range: 3.2237. Min Range: -3.2237

Max Act: 2.8946. Min Act: -0.0000

Data Index: 1548031 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 3.2237. Min Range: -3.2237

Max Act: 2.6227. Min Act: -0.0000

Data Index: 1377370 (Python Code)

Max Activating Token Index: 163

Text #14

Max Range: 3.2237. Min Range: -3.2237

Max Act: 2.7242. Min Act: -0.0000

Data Index: 1385535 (Python Code)

Max Activating Token Index: 260

Text #15

Max Range: 3.2237. Min Range: -3.2237

Max Act: 2.8238. Min Act: -0.0000

Data Index: 1648219 (Python Code)

Max Activating Token Index: 148

Text #16

Max Range: 3.2237. Min Range: -3.2237

Max Act: 2.5484. Min Act: -0.0000

Data Index: 1523103 (Python Code)

Max Activating Token Index: 781

Text #17

Max Range: 3.2237. Min Range: -3.2237

Max Act: 2.7948. Min Act: -0.0000

Data Index: 1445699 (Python Code)

Max Activating Token Index: 442

Text #18

Max Range: 3.2237. Min Range: -3.2237

Max Act: 2.7641. Min Act: -0.0000

Data Index: 1511517 (Python Code)

Max Activating Token Index: 514

Text #19

Max Range: 3.2237. Min Range: -3.2237

Max Act: 2.6260. Min Act: -0.0000

Data Index: 1647265 (Python Code)

Max Activating Token Index: 804