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

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

Neuron 3329 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2910. Min Act: -0.0001

Data Index: 1224882 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2280. Min Act: -0.0001

Data Index: 829853 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2446. Min Act: -0.0001

Data Index: 1532347 (Python Code)

Max Activating Token Index: 565

Text #3

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2545. Min Act: -0.0001

Data Index: 684327 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2017. Min Act: -0.0002

Data Index: 292768 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.1783. Min Act: -0.0001

Data Index: 564798 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.2047. Min Act: -0.0001

Data Index: 1467804 (Python Code)

Max Activating Token Index: 1020

Text #7

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.1872. Min Act: -0.0001

Data Index: 954838 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.1772. Min Act: -0.0001

Data Index: 1274493 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.1787. Min Act: -0.0001

Data Index: 1420140 (Python Code)

Max Activating Token Index: 492

Text #10

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.1629. Min Act: -0.0001

Data Index: 1450162 (Python Code)

Max Activating Token Index: 432

Text #11

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.1770. Min Act: -0.0001

Data Index: 1051401 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.1633. Min Act: -0.0001

Data Index: 1438838 (Python Code)

Max Activating Token Index: 390

Text #13

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.1774. Min Act: -0.0001

Data Index: 1113331 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.1672. Min Act: -0.0001

Data Index: 105011 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.1559. Min Act: -0.0001

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.1520. Min Act: -0.0001

Data Index: 372246 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.1653. Min Act: -0.0001

Data Index: 960841 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.1662. Min Act: -0.0001

Data Index: 1358846 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 0.2910. Min Range: -0.2910

Max Act: 0.1559. Min Act: -0.0001

Data Index: 71972 (C4 (Web Text))

Max Activating Token Index: 388