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

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

Neuron 4578 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1826. Min Act: -0.0000

Data Index: 779254 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1178380 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1130622 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1298467 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1536. Min Act: -0.0000

Data Index: 114578 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1493. Min Act: -0.0000

Data Index: 168426 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1261. Min Act: -0.0000

Data Index: 393525 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1220. Min Act: -0.0000

Data Index: 1077366 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1173. Min Act: -0.0000

Data Index: 807594 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1205. Min Act: -0.0000

Data Index: 526328 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1241. Min Act: -0.0000

Data Index: 216341 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1098. Min Act: -0.0000

Data Index: 53694 (C4 (Web Text))

Max Activating Token Index: 863

Text #12

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1132. Min Act: -0.0000

Data Index: 1089192 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1176. Min Act: -0.0000

Data Index: 462106 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1172. Min Act: -0.0000

Data Index: 1024983 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1131. Min Act: -0.0000

Data Index: 1159252 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1122. Min Act: -0.0000

Data Index: 31102 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1035. Min Act: -0.0000

Data Index: 488139 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1002. Min Act: -0.0000

Data Index: 795304 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.1826. Min Range: -0.1826

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1341501 (C4 (Web Text))

Max Activating Token Index: 912