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

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

Neuron 5720 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1375. Min Act: -0.0000

Data Index: 324751 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1395. Min Act: -0.0000

Data Index: 1201825 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1444881 (Python Code)

Max Activating Token Index: 596

Text #3

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1366. Min Act: -0.0000

Data Index: 693205 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1303. Min Act: -0.0000

Data Index: 442771 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1186. Min Act: -0.0000

Data Index: 143776 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1220. Min Act: -0.0000

Data Index: 1512785 (Python Code)

Max Activating Token Index: 623

Text #7

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1207. Min Act: -0.0000

Data Index: 936653 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1204. Min Act: 0.0000

Data Index: 80660 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1253. Min Act: -0.0000

Data Index: 73501 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1202. Min Act: -0.0000

Data Index: 335918 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1152. Min Act: -0.0000

Data Index: 639872 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1494087 (Python Code)

Max Activating Token Index: 357

Text #13

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1140. Min Act: -0.0000

Data Index: 924142 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1215. Min Act: -0.0000

Data Index: 1004147 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1144993 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1117. Min Act: -0.0000

Data Index: 484664 (C4 (Web Text))

Max Activating Token Index: 249

Text #17

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1102. Min Act: -0.0000

Data Index: 1562840 (Python Code)

Max Activating Token Index: 326

Text #18

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1064. Min Act: -0.0000

Data Index: 1184045 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1095. Min Act: -0.0000

Data Index: 463603 (C4 (Web Text))

Max Activating Token Index: 15