Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 902 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.2948. Min Act: -0.0001

Data Index: 1266153 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.1687. Min Act: -0.0001

Data Index: 231800 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.1749. Min Act: -0.0001

Data Index: 225058 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.0153. Min Act: -0.0001

Data Index: 1263144 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.0217. Min Act: -0.0001

Data Index: 299621 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.0467. Min Act: -0.0001

Data Index: 989710 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.0145. Min Act: -0.0001

Data Index: 187303 (C4 (Web Text))

Max Activating Token Index: 70

Text #7

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.0183. Min Act: -0.0001

Data Index: 32925 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 1.2948. Min Range: -1.2948

Max Act: 1.0087. Min Act: -0.0001

Data Index: 1289484 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.9670. Min Act: -0.0001

Data Index: 1275284 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.9869. Min Act: -0.0001

Data Index: 359061 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.9214. Min Act: -0.0001

Data Index: 139689 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.9811. Min Act: -0.0001

Data Index: 679459 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.8447. Min Act: -0.0001

Data Index: 122831 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.9131. Min Act: -0.0001

Data Index: 929731 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.8673. Min Act: -0.0001

Data Index: 845640 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.8480. Min Act: -0.0001

Data Index: 12912 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.9164. Min Act: -0.0001

Data Index: 294413 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.8742. Min Act: -0.0001

Data Index: 238024 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 1.2948. Min Range: -1.2948

Max Act: 0.8290. Min Act: -0.0001

Data Index: 1167804 (C4 (Web Text))

Max Activating Token Index: 924