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

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

Neuron 2449 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.8120. Min Act: -0.0002

Data Index: 503972 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7591. Min Act: -0.0002

Data Index: 288785 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.8008. Min Act: -0.0002

Data Index: 968383 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7747. Min Act: -0.0002

Data Index: 229012 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7199. Min Act: -0.0002

Data Index: 1302496 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7150. Min Act: -0.0002

Data Index: 1136959 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7484. Min Act: -0.0002

Data Index: 1092621 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7691. Min Act: -0.0002

Data Index: 932887 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7394. Min Act: -0.0002

Data Index: 1109709 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7607. Min Act: -0.0002

Data Index: 488013 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7251. Min Act: -0.0002

Data Index: 923993 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.6802. Min Act: -0.0002

Data Index: 537072 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7441. Min Act: -0.0002

Data Index: 246531 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.6985. Min Act: -0.0002

Data Index: 1109012 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7587. Min Act: -0.0002

Data Index: 560927 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7484. Min Act: -0.0002

Data Index: 617287 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7257. Min Act: -0.0002

Data Index: 1261513 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.6787. Min Act: -0.0002

Data Index: 1210706 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7141. Min Act: -0.0002

Data Index: 693091 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7132. Min Act: -0.0002

Data Index: 509719 (C4 (Web Text))

Max Activating Token Index: 629