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

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

Neuron 1199 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: 0.1410. Min Range: -0.1410

Max Act: 0.1410. Min Act: -0.0001

Data Index: 253909 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1361. Min Act: -0.0000

Data Index: 116194 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1393. Min Act: -0.0000

Data Index: 874788 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1357. Min Act: -0.0000

Data Index: 936238 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1277. Min Act: -0.0000

Data Index: 835661 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1207. Min Act: -0.0000

Data Index: 1307327 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1236. Min Act: -0.0000

Data Index: 333475 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1285. Min Act: -0.0000

Data Index: 821052 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1175. Min Act: -0.0000

Data Index: 872996 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1282400 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1085. Min Act: -0.0000

Data Index: 400550 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1054. Min Act: -0.0000

Data Index: 1097473 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1017499 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1072. Min Act: -0.0000

Data Index: 864407 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1042. Min Act: -0.0000

Data Index: 293110 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1073. Min Act: -0.0001

Data Index: 689818 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0992. Min Act: -0.0000

Data Index: 1183954 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0878. Min Act: -0.0000

Data Index: 614101 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.0995. Min Act: -0.0000

Data Index: 319209 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1029. Min Act: -0.0000

Data Index: 83129 (C4 (Web Text))

Max Activating Token Index: 187