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

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

Neuron 5470 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1322. Min Act: -0.0001

Data Index: 246720 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1236. Min Act: -0.0001

Data Index: 449234 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1100. Min Act: -0.0000

Data Index: 947351 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1071. Min Act: -0.0001

Data Index: 488756 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1032. Min Act: -0.0000

Data Index: 384040 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1085. Min Act: -0.0000

Data Index: 377340 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1023. Min Act: -0.0000

Data Index: 1214971 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1005. Min Act: -0.0000

Data Index: 767315 (C4 (Web Text))

Max Activating Token Index: 320

Text #8

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1024. Min Act: -0.0001

Data Index: 140256 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0990. Min Act: -0.0001

Data Index: 226758 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0971. Min Act: -0.0001

Data Index: 722421 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1189550 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0951. Min Act: -0.0000

Data Index: 974499 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0930. Min Act: -0.0001

Data Index: 333791 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0919. Min Act: -0.0001

Data Index: 147969 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0895. Min Act: -0.0001

Data Index: 743880 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0887. Min Act: -0.0001

Data Index: 426758 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1035351 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0801. Min Act: -0.0000

Data Index: 1165158 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0856. Min Act: -0.0000

Data Index: 812741 (C4 (Web Text))

Max Activating Token Index: 384