Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 304 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1352. Min Act: -0.0002

Data Index: 1556795 (Python Code)

Max Activating Token Index: 659

Text #1

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1305. Min Act: -0.0002

Data Index: 1656275 (Python Code)

Max Activating Token Index: 943

Text #2

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1239. Min Act: -0.0002

Data Index: 1564517 (Python Code)

Max Activating Token Index: 212

Text #3

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1097. Min Act: -0.0002

Data Index: 1636639 (Python Code)

Max Activating Token Index: 716

Text #4

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1109. Min Act: -0.0002

Data Index: 1564017 (Python Code)

Max Activating Token Index: 522

Text #5

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1158. Min Act: -0.0002

Data Index: 1453378 (Python Code)

Max Activating Token Index: 681

Text #6

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1361200 (Python Code)

Max Activating Token Index: 738

Text #7

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1057. Min Act: -0.0002

Data Index: 1375851 (Python Code)

Max Activating Token Index: 449

Text #8

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1047. Min Act: -0.0002

Data Index: 1514258 (Python Code)

Max Activating Token Index: 428

Text #9

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1574328 (Python Code)

Max Activating Token Index: 863

Text #10

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1482045 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1053. Min Act: -0.0002

Data Index: 1465981 (Python Code)

Max Activating Token Index: 359

Text #12

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0992. Min Act: -0.0002

Data Index: 1625495 (Python Code)

Max Activating Token Index: 61

Text #13

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1038. Min Act: -0.0002

Data Index: 1638965 (Python Code)

Max Activating Token Index: 960

Text #14

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1433878 (Python Code)

Max Activating Token Index: 133

Text #15

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1019. Min Act: -0.0002

Data Index: 1585963 (Python Code)

Max Activating Token Index: 382

Text #16

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1494552 (Python Code)

Max Activating Token Index: 622

Text #17

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1012. Min Act: -0.0002

Data Index: 1568118 (Python Code)

Max Activating Token Index: 153

Text #18

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1655478 (Python Code)

Max Activating Token Index: 864

Text #19

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.0961. Min Act: -0.0002

Data Index: 1387452 (Python Code)

Max Activating Token Index: 372