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

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

Neuron 3381 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1797. Min Act: -0.0002

Data Index: 123643 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1727. Min Act: -0.0002

Data Index: 1151622 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1807. Min Act: -0.0002

Data Index: 1494684 (Python Code)

Max Activating Token Index: 395

Text #3

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1773. Min Act: -0.0002

Data Index: 1167376 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1761. Min Act: -0.0002

Data Index: 1411237 (Python Code)

Max Activating Token Index: 336

Text #5

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1738. Min Act: -0.0002

Data Index: 1215189 (C4 (Web Text))

Max Activating Token Index: 465

Text #6

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1800. Min Act: -0.0002

Data Index: 120709 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1719. Min Act: -0.0002

Data Index: 157820 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1648. Min Act: -0.0002

Data Index: 1064633 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1695. Min Act: -0.0002

Data Index: 535029 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1677. Min Act: -0.0002

Data Index: 1652416 (Python Code)

Max Activating Token Index: 251

Text #11

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1634. Min Act: -0.0002

Data Index: 8165 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1599. Min Act: -0.0002

Data Index: 897500 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1630. Min Act: -0.0002

Data Index: 1327681 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1580. Min Act: -0.0002

Data Index: 1069080 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1572. Min Act: -0.0002

Data Index: 1379824 (Python Code)

Max Activating Token Index: 140

Text #16

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1547. Min Act: -0.0002

Data Index: 377732 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1554. Min Act: -0.0002

Data Index: 321412 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1530. Min Act: -0.0002

Data Index: 54539 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 0.1807. Min Range: -0.1807

Max Act: 0.1532. Min Act: -0.0002

Data Index: 216506 (C4 (Web Text))

Max Activating Token Index: 180