Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3937 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1135810 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1354. Min Act: -0.0000

Data Index: 659464 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1257. Min Act: -0.0000

Data Index: 829244 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1263302 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1167. Min Act: -0.0000

Data Index: 1277158 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1266627 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1366498 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1528839 (Python Code)

Max Activating Token Index: 3

Text #8

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1104. Min Act: -0.0000

Data Index: 853058 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1006. Min Act: -0.0001

Data Index: 20258 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1059. Min Act: -0.0000

Data Index: 248243 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1064. Min Act: -0.0001

Data Index: 325131 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1042. Min Act: -0.0000

Data Index: 1151092 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1023. Min Act: -0.0000

Data Index: 34041 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1046. Min Act: -0.0000

Data Index: 51918 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1125. Min Act: -0.0001

Data Index: 830787 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1095409 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1031. Min Act: -0.0001

Data Index: 566145 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1029. Min Act: -0.0000

Data Index: 48717 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.1410. Min Range: -0.1410

Max Act: 0.1028. Min Act: -0.0000

Data Index: 842798 (C4 (Web Text))

Max Activating Token Index: 4