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

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

Neuron 1209 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: 1.9705. Min Range: -1.9705

Max Act: 1.9705. Min Act: -0.0000

Data Index: 787571 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.9361. Min Act: -0.0000

Data Index: 504983 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.8938. Min Act: -0.0000

Data Index: 1265981 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.9565. Min Act: -0.0000

Data Index: 1175903 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.8588. Min Act: -0.0000

Data Index: 788406 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.9628. Min Act: -0.0000

Data Index: 882482 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.7504. Min Act: -0.0000

Data Index: 663817 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.8495. Min Act: -0.0000

Data Index: 616186 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.6287. Min Act: -0.0000

Data Index: 927954 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.9245. Min Act: -0.0000

Data Index: 117279 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.7658. Min Act: -0.0000

Data Index: 1305647 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.8495. Min Act: -0.0000

Data Index: 13912 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.7603. Min Act: -0.0000

Data Index: 391462 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.6577. Min Act: -0.0000

Data Index: 651914 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.7374. Min Act: -0.0000

Data Index: 918768 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.7130. Min Act: -0.0000

Data Index: 541183 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.6933. Min Act: -0.0000

Data Index: 1152301 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.6598. Min Act: -0.0000

Data Index: 483660 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.5641. Min Act: -0.0000

Data Index: 1772 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 1.9705. Min Range: -1.9705

Max Act: 1.7032. Min Act: -0.0000

Data Index: 777945 (C4 (Web Text))

Max Activating Token Index: 727