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

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

Neuron 4762 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.7597. Min Act: -0.0001

Data Index: 1426585 (Python Code)

Max Activating Token Index: 334

Text #1

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5358. Min Act: -0.0001

Data Index: 1489952 (Python Code)

Max Activating Token Index: 650

Text #2

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5218. Min Act: -0.0001

Data Index: 1395131 (Python Code)

Max Activating Token Index: 222

Text #3

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5109. Min Act: -0.0000

Data Index: 1482076 (Python Code)

Max Activating Token Index: 387

Text #4

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5097. Min Act: -0.0001

Data Index: 1378074 (Python Code)

Max Activating Token Index: 545

Text #5

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.4361. Min Act: -0.0001

Data Index: 1450551 (Python Code)

Max Activating Token Index: 655

Text #6

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5347. Min Act: -0.0001

Data Index: 1562162 (Python Code)

Max Activating Token Index: 449

Text #7

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.4170. Min Act: -0.0001

Data Index: 1564230 (Python Code)

Max Activating Token Index: 313

Text #8

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.4778. Min Act: -0.0001

Data Index: 1486973 (Python Code)

Max Activating Token Index: 490

Text #9

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1589297 (Python Code)

Max Activating Token Index: 749

Text #10

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1653835 (Python Code)

Max Activating Token Index: 667

Text #11

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1441008 (Python Code)

Max Activating Token Index: 225

Text #12

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1608776 (Python Code)

Max Activating Token Index: 761

Text #13

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5104. Min Act: -0.0001

Data Index: 1362797 (Python Code)

Max Activating Token Index: 152

Text #14

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.4424. Min Act: -0.0001

Data Index: 1488585 (Python Code)

Max Activating Token Index: 857

Text #15

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1434647 (Python Code)

Max Activating Token Index: 626

Text #16

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.4994. Min Act: -0.0001

Data Index: 1375622 (Python Code)

Max Activating Token Index: 377

Text #17

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.4263. Min Act: -0.0001

Data Index: 1391552 (Python Code)

Max Activating Token Index: 655

Text #18

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.4821. Min Act: -0.0001

Data Index: 1605155 (Python Code)

Max Activating Token Index: 242

Text #19

Max Range: 0.7597. Min Range: -0.7597

Max Act: 0.4809. Min Act: -0.0001

Data Index: 352735 (C4 (Web Text))

Max Activating Token Index: 911