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

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

Neuron 1876 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1546. Min Range: -4.1546

Max Act: 4.1546. Min Act: -0.0000

Data Index: 15958 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 4.1546. Min Range: -4.1546

Max Act: 3.6561. Min Act: -0.0000

Data Index: 1333955 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 4.1546. Min Range: -4.1546

Max Act: 3.6014. Min Act: -0.0000

Data Index: 1109320 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 4.1546. Min Range: -4.1546

Max Act: 3.5443. Min Act: -0.0000

Data Index: 1082444 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 4.1546. Min Range: -4.1546

Max Act: 3.5613. Min Act: -0.0000

Data Index: 720768 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 4.1546. Min Range: -4.1546

Max Act: 3.2396. Min Act: -0.0000

Data Index: 1098861 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 4.1546. Min Range: -4.1546

Max Act: 3.0838. Min Act: -0.0000

Data Index: 171636 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 4.1546. Min Range: -4.1546

Max Act: 2.9134. Min Act: -0.0000

Data Index: 973962 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 4.1546. Min Range: -4.1546

Max Act: 2.8160. Min Act: -0.0000

Data Index: 1119343 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 4.1546. Min Range: -4.1546

Max Act: 2.5228. Min Act: -0.0000

Data Index: 398515 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 4.1546. Min Range: -4.1546

Max Act: 2.6138. Min Act: -0.0000

Data Index: 285795 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 4.1546. Min Range: -4.1546

Max Act: 2.5999. Min Act: -0.0000

Data Index: 1012520 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 4.1546. Min Range: -4.1546

Max Act: 2.5520. Min Act: -0.0000

Data Index: 650992 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 4.1546. Min Range: -4.1546

Max Act: 2.5289. Min Act: -0.0000

Data Index: 1032594 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 4.1546. Min Range: -4.1546

Max Act: 2.4130. Min Act: -0.0000

Data Index: 647138 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 4.1546. Min Range: -4.1546

Max Act: 2.5071. Min Act: -0.0000

Data Index: 19907 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 4.1546. Min Range: -4.1546

Max Act: 2.4665. Min Act: -0.0000

Data Index: 1250062 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 4.1546. Min Range: -4.1546

Max Act: 2.4641. Min Act: -0.0000

Data Index: 1289573 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 4.1546. Min Range: -4.1546

Max Act: 2.3365. Min Act: -0.0000

Data Index: 1213303 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 4.1546. Min Range: -4.1546

Max Act: 2.4476. Min Act: -0.0000

Data Index: 220110 (C4 (Web Text))

Max Activating Token Index: 986