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

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

Neuron 2968 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1938. Min Act: -0.0002

Data Index: 125300 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1550. Min Act: -0.0002

Data Index: 467813 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1389. Min Act: -0.0002

Data Index: 827135 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1410. Min Act: -0.0002

Data Index: 1584660 (Python Code)

Max Activating Token Index: 354

Text #4

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1170. Min Act: -0.0002

Data Index: 497763 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1302. Min Act: -0.0002

Data Index: 1454711 (Python Code)

Max Activating Token Index: 921

Text #6

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1245. Min Act: -0.0002

Data Index: 1577326 (Python Code)

Max Activating Token Index: 281

Text #7

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1288. Min Act: -0.0002

Data Index: 1586254 (Python Code)

Max Activating Token Index: 265

Text #8

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1236. Min Act: -0.0002

Data Index: 1507369 (Python Code)

Max Activating Token Index: 101

Text #9

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1224. Min Act: -0.0002

Data Index: 1061675 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1335. Min Act: -0.0002

Data Index: 1354918 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1181. Min Act: -0.0002

Data Index: 1532887 (Python Code)

Max Activating Token Index: 114

Text #12

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1180. Min Act: -0.0002

Data Index: 1422271 (Python Code)

Max Activating Token Index: 397

Text #13

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1257. Min Act: -0.0002

Data Index: 190084 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1524686 (Python Code)

Max Activating Token Index: 838

Text #15

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1441782 (Python Code)

Max Activating Token Index: 169

Text #16

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1179. Min Act: -0.0002

Data Index: 1375024 (Python Code)

Max Activating Token Index: 550

Text #17

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1220. Min Act: -0.0002

Data Index: 1477590 (Python Code)

Max Activating Token Index: 309

Text #18

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1217. Min Act: -0.0002

Data Index: 1607434 (Python Code)

Max Activating Token Index: 429

Text #19

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1139. Min Act: -0.0002

Data Index: 1526478 (Python Code)

Max Activating Token Index: 790