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

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

Neuron 3645 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.5608. Min Act: -0.0001

Data Index: 286276 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.5231. Min Act: -0.0001

Data Index: 803986 (C4 (Web Text))

Max Activating Token Index: 856

Text #2

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.5222. Min Act: -0.0001

Data Index: 1008831 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4899. Min Act: -0.0001

Data Index: 1333357 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4748. Min Act: -0.0001

Data Index: 1218232 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4677. Min Act: -0.0001

Data Index: 779774 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4484. Min Act: -0.0001

Data Index: 1300649 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4168. Min Act: -0.0001

Data Index: 175022 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4990. Min Act: -0.0001

Data Index: 1255176 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4885. Min Act: -0.0001

Data Index: 1295697 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4486. Min Act: -0.0001

Data Index: 926060 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4726. Min Act: -0.0001

Data Index: 819089 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4508. Min Act: -0.0001

Data Index: 1008180 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4552. Min Act: -0.0001

Data Index: 47884 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4735. Min Act: -0.0001

Data Index: 1025575 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4409. Min Act: -0.0001

Data Index: 1535003 (Python Code)

Max Activating Token Index: 955

Text #16

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4558. Min Act: -0.0001

Data Index: 463815 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4484. Min Act: -0.0001

Data Index: 162052 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4632. Min Act: -0.0001

Data Index: 1103238 (C4 (Web Text))

Max Activating Token Index: 647

Text #19

Max Range: 0.5608. Min Range: -0.5608

Max Act: 0.4496. Min Act: -0.0001

Data Index: 967097 (C4 (Web Text))

Max Activating Token Index: 555