Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3129 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.8350. Min Act: -0.0000

Data Index: 435786 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.8634. Min Act: -0.0000

Data Index: 673415 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7905. Min Act: -0.0000

Data Index: 891834 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.8004. Min Act: -0.0000

Data Index: 483973 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7640. Min Act: -0.0000

Data Index: 436667 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6923. Min Act: -0.0000

Data Index: 683661 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7217. Min Act: -0.0000

Data Index: 110108 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7246. Min Act: -0.0000

Data Index: 543185 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7504. Min Act: -0.0000

Data Index: 162043 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1224718 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.7234. Min Act: -0.0000

Data Index: 655710 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6167. Min Act: -0.0000

Data Index: 1398763 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.5837. Min Act: -0.0000

Data Index: 614024 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6291. Min Act: -0.0000

Data Index: 863997 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6424. Min Act: -0.0000

Data Index: 984072 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6222. Min Act: -0.0000

Data Index: 346489 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6525. Min Act: -0.0000

Data Index: 363812 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1253919 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.6163. Min Act: -0.0000

Data Index: 119154 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.8634. Min Range: -0.8634

Max Act: 0.5972. Min Act: -0.0000

Data Index: 1259343 (C4 (Web Text))

Max Activating Token Index: 114