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

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

Neuron 4763 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1558. Min Act: -0.0002

Data Index: 1507414 (Python Code)

Max Activating Token Index: 939

Text #1

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1526. Min Act: -0.0002

Data Index: 1560106 (Python Code)

Max Activating Token Index: 877

Text #2

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1390. Min Act: -0.0002

Data Index: 1432685 (Python Code)

Max Activating Token Index: 358

Text #3

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1351. Min Act: -0.0002

Data Index: 1471032 (Python Code)

Max Activating Token Index: 133

Text #4

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1337. Min Act: -0.0002

Data Index: 1577642 (Python Code)

Max Activating Token Index: 909

Text #5

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1347. Min Act: -0.0002

Data Index: 1461508 (Python Code)

Max Activating Token Index: 640

Text #6

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1322. Min Act: -0.0002

Data Index: 1618543 (Python Code)

Max Activating Token Index: 841

Text #7

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1273. Min Act: -0.0002

Data Index: 1493274 (Python Code)

Max Activating Token Index: 932

Text #8

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1274. Min Act: -0.0002

Data Index: 1615913 (Python Code)

Max Activating Token Index: 95

Text #9

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1218. Min Act: -0.0002

Data Index: 1462087 (Python Code)

Max Activating Token Index: 783

Text #10

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1223. Min Act: -0.0002

Data Index: 1485343 (Python Code)

Max Activating Token Index: 273

Text #11

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1223. Min Act: -0.0002

Data Index: 1432490 (Python Code)

Max Activating Token Index: 782

Text #12

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1197. Min Act: -0.0002

Data Index: 1053622 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1174. Min Act: -0.0002

Data Index: 1620892 (Python Code)

Max Activating Token Index: 819

Text #14

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1515053 (Python Code)

Max Activating Token Index: 338

Text #15

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1146. Min Act: -0.0002

Data Index: 1538756 (Python Code)

Max Activating Token Index: 347

Text #16

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1137. Min Act: -0.0002

Data Index: 1654165 (Python Code)

Max Activating Token Index: 456

Text #17

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1121. Min Act: -0.0002

Data Index: 1398312 (Python Code)

Max Activating Token Index: 880

Text #18

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1120. Min Act: -0.0002

Data Index: 1543960 (Python Code)

Max Activating Token Index: 856

Text #19

Max Range: 0.1558. Min Range: -0.1558

Max Act: 0.1106. Min Act: -0.0002

Data Index: 928212 (C4 (Web Text))

Max Activating Token Index: 576