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

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

Neuron 2687 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: 0.0715. Min Range: -0.0715

Max Act: 0.0715. Min Act: -0.0002

Data Index: 530200 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0685. Min Act: -0.0002

Data Index: 1419690 (Python Code)

Max Activating Token Index: 134

Text #2

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1273161 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1341028 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1164700 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0628. Min Act: -0.0002

Data Index: 534460 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1439079 (Python Code)

Max Activating Token Index: 219

Text #7

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0625. Min Act: -0.0002

Data Index: 608454 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0631. Min Act: -0.0002

Data Index: 980109 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1575338 (Python Code)

Max Activating Token Index: 472

Text #10

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0624. Min Act: -0.0002

Data Index: 519851 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0630. Min Act: -0.0002

Data Index: 47698 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1383898 (Python Code)

Max Activating Token Index: 765

Text #13

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1094044 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1529234 (Python Code)

Max Activating Token Index: 711

Text #15

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0610. Min Act: -0.0002

Data Index: 587643 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1606370 (Python Code)

Max Activating Token Index: 219

Text #17

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0604. Min Act: -0.0002

Data Index: 994808 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1507351 (Python Code)

Max Activating Token Index: 95

Text #19

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0605. Min Act: -0.0002

Data Index: 708923 (C4 (Web Text))

Max Activating Token Index: 245