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

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

Neuron 3882 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: 4.2286. Min Range: -4.2286

Max Act: 4.2286. Min Act: -0.0001

Data Index: 686421 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.7831. Min Act: -0.0001

Data Index: 1354301 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 4.2286. Min Range: -4.2286

Max Act: 4.0658. Min Act: -0.0001

Data Index: 22359 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.6305. Min Act: -0.0001

Data Index: 784375 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.7033. Min Act: -0.0001

Data Index: 503925 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.5275. Min Act: -0.0001

Data Index: 349305 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.6081. Min Act: -0.0001

Data Index: 1022038 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.2027. Min Act: -0.0001

Data Index: 183434 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.4318. Min Act: -0.0000

Data Index: 376043 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.2707. Min Act: -0.0001

Data Index: 839605 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.5041. Min Act: -0.0001

Data Index: 361940 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.1881. Min Act: -0.0001

Data Index: 850228 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.1578. Min Act: -0.0001

Data Index: 616792 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.1333. Min Act: -0.0000

Data Index: 359263 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.4251. Min Act: -0.0001

Data Index: 279675 (C4 (Web Text))

Max Activating Token Index: 865

Text #15

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.0868. Min Act: -0.0001

Data Index: 1021624 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.2174. Min Act: -0.0001

Data Index: 693794 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 4.2286. Min Range: -4.2286

Max Act: 3.0570. Min Act: -0.0001

Data Index: 595133 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 4.2286. Min Range: -4.2286

Max Act: 2.8849. Min Act: -0.0001

Data Index: 233055 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 4.2286. Min Range: -4.2286

Max Act: 2.9901. Min Act: -0.0001

Data Index: 758578 (C4 (Web Text))

Max Activating Token Index: 52