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

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

Neuron 5424 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: 2.3758. Min Range: -2.3758

Max Act: 2.3758. Min Act: -0.0000

Data Index: 238220 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.3650. Min Act: -0.0000

Data Index: 597844 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.3456. Min Act: -0.0000

Data Index: 1074810 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.2367. Min Act: -0.0000

Data Index: 1040456 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.1177. Min Act: -0.0000

Data Index: 113554 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.1845. Min Act: -0.0000

Data Index: 590231 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.0658. Min Act: -0.0000

Data Index: 651967 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.9270. Min Act: -0.0000

Data Index: 56073 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.1400. Min Act: -0.0000

Data Index: 1284845 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.1222. Min Act: -0.0000

Data Index: 249978 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.0975. Min Act: -0.0000

Data Index: 555965 (C4 (Web Text))

Max Activating Token Index: 360

Text #11

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.0779. Min Act: -0.0000

Data Index: 303033 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.0441. Min Act: -0.0000

Data Index: 688636 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.8941. Min Act: -0.0000

Data Index: 669987 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.9800. Min Act: -0.0000

Data Index: 1280747 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.9638. Min Act: -0.0000

Data Index: 93464 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.9590. Min Act: -0.0000

Data Index: 630512 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.8530. Min Act: -0.0000

Data Index: 893732 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 2.3758. Min Range: -2.3758

Max Act: 2.0562. Min Act: -0.0000

Data Index: 907416 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 2.3758. Min Range: -2.3758

Max Act: 1.8945. Min Act: -0.0000

Data Index: 1207900 (C4 (Web Text))

Max Activating Token Index: 987