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

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

Neuron 56 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.9190. Min Act: -0.0001

Data Index: 506836 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.6379. Min Act: -0.0001

Data Index: 1180368 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.7600. Min Act: -0.0001

Data Index: 810053 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.5771. Min Act: -0.0001

Data Index: 1007497 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.5186. Min Act: -0.0001

Data Index: 20504 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.5168. Min Act: -0.0001

Data Index: 1354085 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.4326. Min Act: -0.0001

Data Index: 37874 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.4351. Min Act: -0.0001

Data Index: 1240464 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.4834. Min Act: -0.0001

Data Index: 778803 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.4813. Min Act: -0.0001

Data Index: 124981 (C4 (Web Text))

Max Activating Token Index: 600

Text #10

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.5134. Min Act: -0.0001

Data Index: 336792 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.4991. Min Act: -0.0001

Data Index: 1155646 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.5245. Min Act: -0.0001

Data Index: 1100346 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.5135. Min Act: -0.0001

Data Index: 1080231 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.4254. Min Act: -0.0001

Data Index: 704940 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.5727. Min Act: -0.0001

Data Index: 17146 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.4917. Min Act: -0.0001

Data Index: 708331 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.5026. Min Act: -0.0001

Data Index: 302784 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.4202. Min Act: -0.0001

Data Index: 19304 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 1.9190. Min Range: -1.9190

Max Act: 1.4498. Min Act: -0.0001

Data Index: 918364 (C4 (Web Text))

Max Activating Token Index: 419