Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1501 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.7274. Min Act: -0.0001

Data Index: 238773 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.6592. Min Act: -0.0001

Data Index: 528182 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.5395. Min Act: -0.0001

Data Index: 957727 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.5308. Min Act: -0.0000

Data Index: 627056 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.4689. Min Act: -0.0000

Data Index: 65744 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.4340. Min Act: -0.0000

Data Index: 407195 (C4 (Web Text))

Max Activating Token Index: 129

Text #6

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.2180. Min Act: -0.0000

Data Index: 1102685 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.2928. Min Act: -0.0001

Data Index: 1245751 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.2345. Min Act: -0.0000

Data Index: 898763 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.1597. Min Act: -0.0001

Data Index: 110289 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.1574. Min Act: -0.0001

Data Index: 975550 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.1285. Min Act: -0.0000

Data Index: 1115672 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1298601 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.1995. Min Act: -0.0000

Data Index: 331607 (C4 (Web Text))

Max Activating Token Index: 293

Text #14

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.2309. Min Act: -0.0000

Data Index: 72303 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.2724. Min Act: -0.0001

Data Index: 591168 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.0947. Min Act: -0.0000

Data Index: 852540 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.0896. Min Act: -0.0000

Data Index: 1300437 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.1088. Min Act: -0.0000

Data Index: 696015 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 1.7274. Min Range: -1.7274

Max Act: 1.1045. Min Act: -0.0001

Data Index: 386532 (C4 (Web Text))

Max Activating Token Index: 287