Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 575 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1582969 (Python Code)

Max Activating Token Index: 346

Text #1

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1404008 (Python Code)

Max Activating Token Index: 163

Text #2

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1260. Min Act: -0.0001

Data Index: 1385093 (Python Code)

Max Activating Token Index: 1006

Text #3

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1444398 (Python Code)

Max Activating Token Index: 282

Text #4

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1177. Min Act: -0.0001

Data Index: 1374267 (Python Code)

Max Activating Token Index: 778

Text #5

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0973. Min Act: -0.0001

Data Index: 1597943 (Python Code)

Max Activating Token Index: 852

Text #6

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1446888 (Python Code)

Max Activating Token Index: 516

Text #7

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1017. Min Act: -0.0001

Data Index: 1611809 (Python Code)

Max Activating Token Index: 790

Text #8

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1372496 (Python Code)

Max Activating Token Index: 557

Text #9

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1582758 (Python Code)

Max Activating Token Index: 192

Text #10

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1368251 (Python Code)

Max Activating Token Index: 609

Text #11

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1459614 (Python Code)

Max Activating Token Index: 969

Text #12

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1120. Min Act: -0.0001

Data Index: 1551736 (Python Code)

Max Activating Token Index: 781

Text #13

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1394088 (Python Code)

Max Activating Token Index: 563

Text #14

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1531055 (Python Code)

Max Activating Token Index: 902

Text #15

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1481863 (Python Code)

Max Activating Token Index: 725

Text #16

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1419199 (Python Code)

Max Activating Token Index: 173

Text #17

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1013. Min Act: -0.0001

Data Index: 1476462 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.1035. Min Act: -0.0001

Data Index: 676167 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.1338. Min Range: -0.1338

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1066248 (C4 (Web Text))

Max Activating Token Index: 796