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

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

Neuron 1254 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1640980 (Python Code)

Max Activating Token Index: 165

Text #1

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1251. Min Act: -0.0001

Data Index: 322067 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1275. Min Act: -0.0001

Data Index: 1513492 (Python Code)

Max Activating Token Index: 863

Text #3

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1581021 (Python Code)

Max Activating Token Index: 95

Text #4

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1028477 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1285. Min Act: -0.0001

Data Index: 1228021 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1370. Min Act: -0.0001

Data Index: 641220 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1587109 (Python Code)

Max Activating Token Index: 742

Text #8

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1381163 (Python Code)

Max Activating Token Index: 658

Text #9

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1286125 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1233. Min Act: -0.0001

Data Index: 1565526 (Python Code)

Max Activating Token Index: 503

Text #11

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1188. Min Act: -0.0001

Data Index: 406931 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1309. Min Act: -0.0001

Data Index: 1419724 (Python Code)

Max Activating Token Index: 466

Text #13

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1106. Min Act: -0.0001

Data Index: 381538 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1592542 (Python Code)

Max Activating Token Index: 1015

Text #15

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1153. Min Act: -0.0001

Data Index: 1521477 (Python Code)

Max Activating Token Index: 71

Text #16

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1260. Min Act: -0.0001

Data Index: 747753 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1077. Min Act: -0.0001

Data Index: 1592628 (Python Code)

Max Activating Token Index: 823

Text #18

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1188. Min Act: -0.0001

Data Index: 1404206 (Python Code)

Max Activating Token Index: 734

Text #19

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1024. Min Act: -0.0001

Data Index: 1597625 (Python Code)

Max Activating Token Index: 748