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

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

Neuron 1852 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: 1.6047. Min Range: -1.6047

Max Act: 1.5699. Min Act: -0.0000

Data Index: 1228553 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.6047. Min Act: -0.0000

Data Index: 908997 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.5877. Min Act: -0.0000

Data Index: 292896 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.5810. Min Act: -0.0001

Data Index: 631983 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.5648. Min Act: -0.0000

Data Index: 562292 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.5560. Min Act: -0.0000

Data Index: 820920 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.4615. Min Act: -0.0000

Data Index: 734882 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.5404. Min Act: -0.0000

Data Index: 472539 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.4121. Min Act: -0.0000

Data Index: 595894 (C4 (Web Text))

Max Activating Token Index: 362

Text #9

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.5834. Min Act: -0.0000

Data Index: 919032 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.4099. Min Act: -0.0000

Data Index: 1211049 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.4737. Min Act: -0.0000

Data Index: 832709 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.4707. Min Act: -0.0000

Data Index: 1287828 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.4777. Min Act: -0.0000

Data Index: 534942 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.4492. Min Act: -0.0000

Data Index: 356 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.4364. Min Act: -0.0000

Data Index: 994095 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.3852. Min Act: -0.0000

Data Index: 981148 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.4034. Min Act: -0.0000

Data Index: 672078 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.4162. Min Act: -0.0001

Data Index: 257322 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 1.6047. Min Range: -1.6047

Max Act: 1.3326. Min Act: -0.0000

Data Index: 1243359 (C4 (Web Text))

Max Activating Token Index: 835