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

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

Neuron 4910 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: 3.9143. Min Range: -3.9143

Max Act: 3.9143. Min Act: -0.0000

Data Index: 1055155 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 3.9143. Min Range: -3.9143

Max Act: 2.9187. Min Act: -0.0000

Data Index: 766065 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 3.9143. Min Range: -3.9143

Max Act: 2.5944. Min Act: -0.0000

Data Index: 1184480 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 3.9143. Min Range: -3.9143

Max Act: 2.2175. Min Act: -0.0000

Data Index: 1127183 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 3.9143. Min Range: -3.9143

Max Act: 2.1599. Min Act: -0.0000

Data Index: 182206 (C4 (Web Text))

Max Activating Token Index: 797

Text #5

Max Range: 3.9143. Min Range: -3.9143

Max Act: 1.8829. Min Act: -0.0000

Data Index: 292067 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 3.9143. Min Range: -3.9143

Max Act: 2.0759. Min Act: -0.0000

Data Index: 135463 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 3.9143. Min Range: -3.9143

Max Act: 2.1458. Min Act: -0.0000

Data Index: 1120146 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 3.9143. Min Range: -3.9143

Max Act: 2.1629. Min Act: -0.0000

Data Index: 909121 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 3.9143. Min Range: -3.9143

Max Act: 2.0004. Min Act: -0.0000

Data Index: 578938 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 3.9143. Min Range: -3.9143

Max Act: 1.9824. Min Act: -0.0000

Data Index: 233815 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 3.9143. Min Range: -3.9143

Max Act: 1.9701. Min Act: -0.0000

Data Index: 886479 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 3.9143. Min Range: -3.9143

Max Act: 1.8600. Min Act: -0.0000

Data Index: 168637 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 3.9143. Min Range: -3.9143

Max Act: 1.8414. Min Act: -0.0000

Data Index: 601513 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 3.9143. Min Range: -3.9143

Max Act: 1.8483. Min Act: -0.0000

Data Index: 798193 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 3.9143. Min Range: -3.9143

Max Act: 2.0666. Min Act: -0.0000

Data Index: 118277 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 3.9143. Min Range: -3.9143

Max Act: 1.9174. Min Act: -0.0000

Data Index: 794483 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 3.9143. Min Range: -3.9143

Max Act: 1.8141. Min Act: -0.0000

Data Index: 308501 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 3.9143. Min Range: -3.9143

Max Act: 2.0303. Min Act: -0.0000

Data Index: 152155 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 3.9143. Min Range: -3.9143

Max Act: 1.9098. Min Act: -0.0000

Data Index: 781833 (C4 (Web Text))

Max Activating Token Index: 407