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

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

Neuron 5336 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: 2.8010. Min Range: -2.8010

Max Act: 2.7269. Min Act: -0.0000

Data Index: 899076 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.5601. Min Act: -0.0000

Data Index: 402664 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.8010. Min Act: -0.0000

Data Index: 599695 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.5481. Min Act: -0.0000

Data Index: 870441 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.4041. Min Act: -0.0000

Data Index: 437314 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.3311. Min Act: -0.0000

Data Index: 269277 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.2916. Min Act: -0.0000

Data Index: 878907 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.2978. Min Act: -0.0000

Data Index: 659268 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.2583. Min Act: -0.0000

Data Index: 54757 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.2440. Min Act: -0.0000

Data Index: 315261 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.2315. Min Act: -0.0000

Data Index: 715722 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.1806. Min Act: -0.0000

Data Index: 562806 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.1967. Min Act: -0.0000

Data Index: 352544 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.0447. Min Act: -0.0000

Data Index: 1262113 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.0559. Min Act: -0.0000

Data Index: 214252 (C4 (Web Text))

Max Activating Token Index: 540

Text #15

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.1251. Min Act: -0.0000

Data Index: 1091734 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.1251. Min Act: -0.0000

Data Index: 244245 (C4 (Web Text))

Max Activating Token Index: 180

Text #17

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.1135. Min Act: -0.0000

Data Index: 713263 (C4 (Web Text))

Max Activating Token Index: 162

Text #18

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.1087. Min Act: -0.0000

Data Index: 356535 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 2.8010. Min Range: -2.8010

Max Act: 2.2126. Min Act: -0.0000

Data Index: 147217 (C4 (Web Text))

Max Activating Token Index: 946