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

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

Neuron 1484 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1863. Min Act: -0.0000

Data Index: 71473 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1144906 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1490426 (Python Code)

Max Activating Token Index: 443

Text #3

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1079752 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1379. Min Act: -0.0000

Data Index: 286851 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1423. Min Act: -0.0000

Data Index: 272779 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1091363 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1600614 (Python Code)

Max Activating Token Index: 933

Text #8

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1287. Min Act: -0.0000

Data Index: 1004904 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1219. Min Act: -0.0000

Data Index: 99738 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1114. Min Act: -0.0000

Data Index: 521578 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1173. Min Act: -0.0000

Data Index: 312120 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1341520 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1205. Min Act: -0.0000

Data Index: 516799 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1108. Min Act: -0.0000

Data Index: 511976 (C4 (Web Text))

Max Activating Token Index: 597

Text #15

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1085. Min Act: -0.0000

Data Index: 927293 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1511526 (Python Code)

Max Activating Token Index: 938

Text #17

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.0990. Min Act: -0.0000

Data Index: 248651 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1015. Min Act: -0.0000

Data Index: 166896 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.1863. Min Range: -0.1863

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1504315 (Python Code)

Max Activating Token Index: 963