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

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

Neuron 3238 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1577229 (Python Code)

Max Activating Token Index: 469

Text #1

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6881. Min Act: -0.0000

Data Index: 1057521 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1563079 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6216. Min Act: 0.0000

Data Index: 1654377 (Python Code)

Max Activating Token Index: 417

Text #4

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6150. Min Act: 0.0000

Data Index: 1393494 (Python Code)

Max Activating Token Index: 256

Text #5

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.6207. Min Act: -0.0000

Data Index: 1516846 (Python Code)

Max Activating Token Index: 367

Text #6

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5363. Min Act: -0.0000

Data Index: 1636637 (Python Code)

Max Activating Token Index: 812

Text #7

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5215. Min Act: 0.0001

Data Index: 1468495 (Python Code)

Max Activating Token Index: 767

Text #8

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5265. Min Act: 0.0000

Data Index: 1636874 (Python Code)

Max Activating Token Index: 16

Text #9

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5436. Min Act: 0.0000

Data Index: 1416885 (Python Code)

Max Activating Token Index: 391

Text #10

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5393. Min Act: 0.0000

Data Index: 1644220 (Python Code)

Max Activating Token Index: 771

Text #11

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1508969 (Python Code)

Max Activating Token Index: 417

Text #12

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5016. Min Act: -0.0000

Data Index: 886604 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.5154. Min Act: 0.0000

Data Index: 1520050 (Python Code)

Max Activating Token Index: 902

Text #14

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1427539 (Python Code)

Max Activating Token Index: 579

Text #15

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4982. Min Act: 0.0000

Data Index: 1619733 (Python Code)

Max Activating Token Index: 204

Text #16

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1503514 (Python Code)

Max Activating Token Index: 126

Text #17

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1544289 (Python Code)

Max Activating Token Index: 410

Text #18

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4118. Min Act: 0.0000

Data Index: 615884 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 0.6881. Min Range: -0.6881

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1428687 (Python Code)

Max Activating Token Index: 460