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

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

Neuron 1983 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8002. Min Range: -2.8002

Max Act: 2.8002. Min Act: -0.0000

Data Index: 1345896 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 2.8002. Min Range: -2.8002

Max Act: 2.5985. Min Act: -0.0000

Data Index: 568862 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 2.8002. Min Range: -2.8002

Max Act: 2.2981. Min Act: -0.0000

Data Index: 412941 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 2.8002. Min Range: -2.8002

Max Act: 1.9809. Min Act: -0.0000

Data Index: 261034 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 2.8002. Min Range: -2.8002

Max Act: 2.0582. Min Act: -0.0000

Data Index: 1082742 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 2.8002. Min Range: -2.8002

Max Act: 2.0193. Min Act: -0.0000

Data Index: 544209 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 2.8002. Min Range: -2.8002

Max Act: 1.7497. Min Act: -0.0000

Data Index: 440785 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 2.8002. Min Range: -2.8002

Max Act: 1.8378. Min Act: -0.0000

Data Index: 687598 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 2.8002. Min Range: -2.8002

Max Act: 2.1402. Min Act: -0.0000

Data Index: 48212 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 2.8002. Min Range: -2.8002

Max Act: 1.8875. Min Act: -0.0000

Data Index: 979683 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 2.8002. Min Range: -2.8002

Max Act: 1.7187. Min Act: -0.0000

Data Index: 401349 (C4 (Web Text))

Max Activating Token Index: 546

Text #11

Max Range: 2.8002. Min Range: -2.8002

Max Act: 1.8742. Min Act: -0.0000

Data Index: 817250 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 2.8002. Min Range: -2.8002

Max Act: 1.7543. Min Act: -0.0000

Data Index: 1344971 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 2.8002. Min Range: -2.8002

Max Act: 1.6067. Min Act: -0.0000

Data Index: 935851 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 2.8002. Min Range: -2.8002

Max Act: 1.6010. Min Act: -0.0000

Data Index: 1205256 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 2.8002. Min Range: -2.8002

Max Act: 1.5156. Min Act: -0.0000

Data Index: 518917 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 2.8002. Min Range: -2.8002

Max Act: 1.5893. Min Act: -0.0000

Data Index: 553432 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 2.8002. Min Range: -2.8002

Max Act: 1.6691. Min Act: -0.0000

Data Index: 365437 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 2.8002. Min Range: -2.8002

Max Act: 1.5421. Min Act: -0.0000

Data Index: 1331604 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 2.8002. Min Range: -2.8002

Max Act: 1.6488. Min Act: -0.0000

Data Index: 246892 (C4 (Web Text))

Max Activating Token Index: 744