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

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

Neuron 1323 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: 0.1513. Min Range: -0.1513

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1257681 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1303. Min Act: -0.0000

Data Index: 614699 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1285. Min Act: -0.0001

Data Index: 511590 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1030628 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1312. Min Act: -0.0001

Data Index: 880833 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1285. Min Act: -0.0001

Data Index: 570231 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1239. Min Act: -0.0001

Data Index: 795219 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1188. Min Act: -0.0001

Data Index: 94857 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1166663 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1193. Min Act: -0.0001

Data Index: 927111 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1178. Min Act: -0.0001

Data Index: 316035 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1172. Min Act: -0.0000

Data Index: 1068441 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1137. Min Act: 0.0001

Data Index: 87927 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1144. Min Act: -0.0001

Data Index: 1098721 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1136. Min Act: -0.0000

Data Index: 223103 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1111. Min Act: -0.0001

Data Index: 379258 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1115. Min Act: -0.0001

Data Index: 552815 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1101. Min Act: -0.0001

Data Index: 1127950 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.0981. Min Act: -0.0001

Data Index: 489344 (C4 (Web Text))

Max Activating Token Index: 528

Text #19

Max Range: 0.1513. Min Range: -0.1513

Max Act: 0.1076. Min Act: -0.0000

Data Index: 287576 (C4 (Web Text))

Max Activating Token Index: 407