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

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

Neuron 705 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.2114. Min Act: -0.0001

Data Index: 173487 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.2093. Min Act: -0.0001

Data Index: 1232898 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1920. Min Act: -0.0001

Data Index: 87069 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1805. Min Act: -0.0001

Data Index: 523715 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1997. Min Act: -0.0002

Data Index: 1199877 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1702. Min Act: -0.0001

Data Index: 819175 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1560. Min Act: -0.0001

Data Index: 368838 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1775. Min Act: -0.0001

Data Index: 359791 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1619. Min Act: -0.0001

Data Index: 1460201 (Python Code)

Max Activating Token Index: 20

Text #9

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1729. Min Act: -0.0002

Data Index: 450728 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1640. Min Act: -0.0001

Data Index: 783661 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1613. Min Act: -0.0002

Data Index: 852399 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1660. Min Act: -0.0001

Data Index: 402746 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1642. Min Act: -0.0002

Data Index: 16800 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1574. Min Act: -0.0002

Data Index: 325126 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1409316 (Python Code)

Max Activating Token Index: 1000

Text #16

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1498351 (Python Code)

Max Activating Token Index: 29

Text #17

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1727. Min Act: -0.0001

Data Index: 903444 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1561. Min Act: -0.0002

Data Index: 1139174 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.2114. Min Range: -0.2114

Max Act: 0.1498. Min Act: -0.0001

Data Index: 1531864 (Python Code)

Max Activating Token Index: 21