Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 642 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.7593. Min Act: -0.0001

Data Index: 94446 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.6430. Min Act: -0.0000

Data Index: 830695 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.3423. Min Act: -0.0000

Data Index: 369989 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.3579. Min Act: -0.0000

Data Index: 170199 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.3850. Min Act: -0.0001

Data Index: 599139 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.1236. Min Act: -0.0000

Data Index: 171722 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.3824. Min Act: -0.0000

Data Index: 918424 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.0537. Min Act: -0.0000

Data Index: 894120 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.1481. Min Act: -0.0000

Data Index: 502397 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.1457. Min Act: -0.0001

Data Index: 484821 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.0686. Min Act: -0.0000

Data Index: 669413 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.0538. Min Act: -0.0000

Data Index: 137452 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 1.7593. Min Range: -1.7593

Max Act: 0.9896. Min Act: -0.0000

Data Index: 303527 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.0056. Min Act: -0.0000

Data Index: 1230122 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.0317. Min Act: -0.0000

Data Index: 98104 (C4 (Web Text))

Max Activating Token Index: 186

Text #15

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.0410. Min Act: -0.0000

Data Index: 1171943 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 1.7593. Min Range: -1.7593

Max Act: 1.0003. Min Act: -0.0000

Data Index: 358616 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 1.7593. Min Range: -1.7593

Max Act: 0.9252. Min Act: -0.0000

Data Index: 158355 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 1.7593. Min Range: -1.7593

Max Act: 0.8831. Min Act: -0.0000

Data Index: 519262 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 1.7593. Min Range: -1.7593

Max Act: 0.9208. Min Act: -0.0000

Data Index: 634667 (C4 (Web Text))

Max Activating Token Index: 834