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

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

Neuron 4699 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3020. Min Range: -2.3020

Max Act: 2.3020. Min Act: -0.0000

Data Index: 124703 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.8599. Min Act: 0.0000

Data Index: 1003456 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.8939. Min Act: -0.0000

Data Index: 481790 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.8765. Min Act: -0.0000

Data Index: 910602 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.5311. Min Act: -0.0000

Data Index: 546462 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.4519. Min Act: -0.0000

Data Index: 789358 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.3555. Min Act: 0.0000

Data Index: 687532 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.3491. Min Act: -0.0000

Data Index: 560063 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.3342. Min Act: -0.0000

Data Index: 8216 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.3094. Min Act: -0.0000

Data Index: 89664 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.2127. Min Act: 0.0002

Data Index: 1332226 (C4 (Web Text))

Max Activating Token Index: 288

Text #11

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.2741. Min Act: -0.0000

Data Index: 783085 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.2720. Min Act: -0.0000

Data Index: 665607 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.2707. Min Act: -0.0000

Data Index: 1160048 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.2342. Min Act: -0.0000

Data Index: 83202 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.3052. Min Act: -0.0000

Data Index: 103285 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.2848. Min Act: 0.0000

Data Index: 1329167 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.2165. Min Act: -0.0000

Data Index: 508382 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.1812. Min Act: 0.0000

Data Index: 980484 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 2.3020. Min Range: -2.3020

Max Act: 1.0969. Min Act: -0.0000

Data Index: 173270 (C4 (Web Text))

Max Activating Token Index: 351