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

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

Neuron 2726 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: 0.1352. Min Range: -0.1352

Max Act: 0.1352. Min Act: -0.0001

Data Index: 99610 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1268. Min Act: -0.0001

Data Index: 755283 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1148211 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1189. Min Act: -0.0001

Data Index: 1086091 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1194. Min Act: -0.0001

Data Index: 1198040 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1288878 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1234137 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1111. Min Act: -0.0001

Data Index: 316674 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1188. Min Act: -0.0001

Data Index: 470058 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1138. Min Act: -0.0001

Data Index: 1013460 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1358318 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1131. Min Act: -0.0001

Data Index: 757659 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1202. Min Act: -0.0001

Data Index: 482273 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1099. Min Act: -0.0001

Data Index: 995567 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1089. Min Act: -0.0001

Data Index: 617787 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1123. Min Act: -0.0001

Data Index: 1304775 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1130. Min Act: -0.0001

Data Index: 800488 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1097. Min Act: -0.0001

Data Index: 699873 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1025. Min Act: -0.0001

Data Index: 640252 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.1352. Min Range: -0.1352

Max Act: 0.1095. Min Act: -0.0001

Data Index: 20953 (C4 (Web Text))

Max Activating Token Index: 479