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

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

Neuron 3458 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1512. Min Act: -0.0002

Data Index: 828859 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.1355. Min Act: -0.0003

Data Index: 955113 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1380361 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1649355 (Python Code)

Max Activating Token Index: 508

Text #4

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1435972 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1615902 (Python Code)

Max Activating Token Index: 734

Text #6

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1612466 (Python Code)

Max Activating Token Index: 573

Text #7

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1644419 (Python Code)

Max Activating Token Index: 559

Text #8

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1361182 (Python Code)

Max Activating Token Index: 572

Text #9

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0771. Min Act: -0.0002

Data Index: 1567992 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1375151 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0711. Min Act: -0.0001

Data Index: 1431908 (Python Code)

Max Activating Token Index: 715

Text #12

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1360104 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1506008 (Python Code)

Max Activating Token Index: 299

Text #14

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0679. Min Act: -0.0001

Data Index: 1622472 (Python Code)

Max Activating Token Index: 683

Text #15

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1510306 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1592576 (Python Code)

Max Activating Token Index: 532

Text #17

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1387655 (Python Code)

Max Activating Token Index: 374

Text #18

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1445847 (Python Code)

Max Activating Token Index: 339

Text #19

Max Range: 0.1512. Min Range: -0.1512

Max Act: 0.0667. Min Act: -0.0001

Data Index: 1576435 (Python Code)

Max Activating Token Index: 597