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

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

Neuron 2057 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1503. Min Act: -0.0003

Data Index: 1649485 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1445. Min Act: -0.0002

Data Index: 1448223 (Python Code)

Max Activating Token Index: 25

Text #2

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1553772 (Python Code)

Max Activating Token Index: 18

Text #3

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1216. Min Act: -0.0003

Data Index: 1403687 (Python Code)

Max Activating Token Index: 85

Text #4

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1257. Min Act: -0.0003

Data Index: 1492409 (Python Code)

Max Activating Token Index: 270

Text #5

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1190. Min Act: -0.0003

Data Index: 1447067 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1231. Min Act: -0.0002

Data Index: 1588189 (Python Code)

Max Activating Token Index: 592

Text #7

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1224. Min Act: -0.0002

Data Index: 1629643 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1209. Min Act: -0.0003

Data Index: 1479156 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1179. Min Act: -0.0002

Data Index: 1597872 (Python Code)

Max Activating Token Index: 204

Text #10

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1209. Min Act: -0.0003

Data Index: 1466280 (Python Code)

Max Activating Token Index: 370

Text #11

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1193. Min Act: -0.0003

Data Index: 1428842 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1175. Min Act: -0.0003

Data Index: 1481054 (Python Code)

Max Activating Token Index: 27

Text #13

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1113. Min Act: -0.0003

Data Index: 1385164 (Python Code)

Max Activating Token Index: 228

Text #14

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1093. Min Act: -0.0003

Data Index: 1518992 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1131. Min Act: -0.0003

Data Index: 1605329 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1118. Min Act: -0.0002

Data Index: 1382813 (Python Code)

Max Activating Token Index: 216

Text #17

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1063. Min Act: -0.0003

Data Index: 1544635 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1066. Min Act: -0.0002

Data Index: 1385098 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 0.1503. Min Range: -0.1503

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1621630 (Python Code)

Max Activating Token Index: 54