Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 550 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.7715. Min Act: -0.0001

Data Index: 1145991 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.7498. Min Act: -0.0001

Data Index: 777043 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.7105. Min Act: -0.0001

Data Index: 820215 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.7035. Min Act: -0.0001

Data Index: 784398 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.7045. Min Act: -0.0001

Data Index: 672006 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.7401. Min Act: -0.0001

Data Index: 578086 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6617. Min Act: -0.0001

Data Index: 685817 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.7224. Min Act: -0.0001

Data Index: 613562 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6579. Min Act: -0.0001

Data Index: 1021912 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6737. Min Act: -0.0001

Data Index: 688339 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6517. Min Act: -0.0001

Data Index: 1105659 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6462. Min Act: -0.0001

Data Index: 986686 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6465. Min Act: -0.0001

Data Index: 1062089 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6440. Min Act: -0.0001

Data Index: 1029408 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6496. Min Act: -0.0001

Data Index: 1096765 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6379. Min Act: -0.0001

Data Index: 1027994 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6234. Min Act: -0.0001

Data Index: 342616 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6370. Min Act: -0.0001

Data Index: 1088210 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6429. Min Act: -0.0001

Data Index: 1229934 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.7715. Min Range: -0.7715

Max Act: 0.6492. Min Act: -0.0001

Data Index: 1341907 (C4 (Web Text))

Max Activating Token Index: 796