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

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

Neuron 1711 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: 1.0649. Min Range: -1.0649

Max Act: 1.0649. Min Act: -0.0000

Data Index: 398634 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 1.0649. Min Range: -1.0649

Max Act: 1.0440. Min Act: -0.0000

Data Index: 622735 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 1.0649. Min Range: -1.0649

Max Act: 1.0256. Min Act: -0.0000

Data Index: 1450985 (Python Code)

Max Activating Token Index: 1006

Text #3

Max Range: 1.0649. Min Range: -1.0649

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1435147 (Python Code)

Max Activating Token Index: 194

Text #4

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.9678. Min Act: -0.0000

Data Index: 394156 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.9686. Min Act: -0.0000

Data Index: 1421621 (Python Code)

Max Activating Token Index: 824

Text #6

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.9281. Min Act: -0.0000

Data Index: 1289057 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 1.0649. Min Range: -1.0649

Max Act: 1.0354. Min Act: -0.0000

Data Index: 519167 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 1.0649. Min Range: -1.0649

Max Act: 1.0029. Min Act: -0.0000

Data Index: 1371848 (Python Code)

Max Activating Token Index: 532

Text #9

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1468820 (Python Code)

Max Activating Token Index: 172

Text #10

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.9361. Min Act: -0.0000

Data Index: 522831 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.9734. Min Act: -0.0000

Data Index: 1470434 (Python Code)

Max Activating Token Index: 633

Text #12

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.9763. Min Act: -0.0000

Data Index: 5782 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.9707. Min Act: -0.0000

Data Index: 407350 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.8911. Min Act: -0.0000

Data Index: 89556 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.9498. Min Act: -0.0000

Data Index: 1442331 (Python Code)

Max Activating Token Index: 346

Text #16

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.8846. Min Act: -0.0000

Data Index: 856121 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.9458. Min Act: -0.0000

Data Index: 711795 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.9240. Min Act: -0.0000

Data Index: 1519498 (Python Code)

Max Activating Token Index: 49

Text #19

Max Range: 1.0649. Min Range: -1.0649

Max Act: 0.8896. Min Act: -0.0000

Data Index: 21857 (C4 (Web Text))

Max Activating Token Index: 336