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

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

Neuron 4673 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0219. Min Range: -1.0219

Max Act: 1.0219. Min Act: -0.0000

Data Index: 1585670 (Python Code)

Max Activating Token Index: 990

Text #1

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1453786 (Python Code)

Max Activating Token Index: 644

Text #2

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.9594. Min Act: -0.0000

Data Index: 1544207 (Python Code)

Max Activating Token Index: 701

Text #3

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1640489 (Python Code)

Max Activating Token Index: 541

Text #4

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.9071. Min Act: -0.0000

Data Index: 1536663 (Python Code)

Max Activating Token Index: 569

Text #5

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8804. Min Act: -0.0000

Data Index: 1502985 (Python Code)

Max Activating Token Index: 820

Text #6

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8315. Min Act: -0.0000

Data Index: 1593724 (Python Code)

Max Activating Token Index: 620

Text #7

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1619656 (Python Code)

Max Activating Token Index: 196

Text #8

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1434095 (Python Code)

Max Activating Token Index: 515

Text #9

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1453782 (Python Code)

Max Activating Token Index: 992

Text #10

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1533680 (Python Code)

Max Activating Token Index: 602

Text #11

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1456262 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1360934 (Python Code)

Max Activating Token Index: 243

Text #13

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1630968 (Python Code)

Max Activating Token Index: 115

Text #14

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.7611. Min Act: -0.0000

Data Index: 1408319 (Python Code)

Max Activating Token Index: 210

Text #15

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1623781 (Python Code)

Max Activating Token Index: 979

Text #16

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8169. Min Act: -0.0000

Data Index: 1600113 (Python Code)

Max Activating Token Index: 985

Text #17

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1439354 (Python Code)

Max Activating Token Index: 797

Text #18

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.8343. Min Act: -0.0000

Data Index: 1401032 (Python Code)

Max Activating Token Index: 367

Text #19

Max Range: 1.0219. Min Range: -1.0219

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1400293 (Python Code)

Max Activating Token Index: 998