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

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

Neuron 5987 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.2290. Min Act: -0.0000

Data Index: 422735 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1390. Min Act: -0.0000

Data Index: 63007 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1485. Min Act: -0.0000

Data Index: 205348 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1361. Min Act: -0.0000

Data Index: 359134 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1380. Min Act: -0.0000

Data Index: 993577 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1255. Min Act: -0.0000

Data Index: 1065684 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1172. Min Act: -0.0000

Data Index: 65788 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1127. Min Act: -0.0000

Data Index: 764840 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1178. Min Act: -0.0000

Data Index: 880119 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1143. Min Act: -0.0000

Data Index: 912428 (C4 (Web Text))

Max Activating Token Index: 212

Text #10

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1137. Min Act: -0.0000

Data Index: 793639 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1032494 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1247. Min Act: -0.0000

Data Index: 1109472 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1115. Min Act: -0.0000

Data Index: 278891 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1112. Min Act: -0.0000

Data Index: 269880 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1132. Min Act: -0.0000

Data Index: 192860 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1500888 (Python Code)

Max Activating Token Index: 525

Text #17

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1046. Min Act: -0.0000

Data Index: 104849 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1007. Min Act: -0.0000

Data Index: 666548 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1267228 (C4 (Web Text))

Max Activating Token Index: 763