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

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

Neuron 5062 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.8537. Min Act: -0.0000

Data Index: 633852 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.7342. Min Act: -0.0000

Data Index: 778799 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6993. Min Act: -0.0000

Data Index: 566633 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6799. Min Act: -0.0000

Data Index: 400763 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6805. Min Act: -0.0000

Data Index: 33248 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6692. Min Act: -0.0000

Data Index: 756653 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1359624 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6407. Min Act: -0.0000

Data Index: 53272 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1284354 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1359176 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5999. Min Act: -0.0000

Data Index: 629091 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6000. Min Act: -0.0000

Data Index: 194859 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.6119. Min Act: -0.0000

Data Index: 628322 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5717. Min Act: -0.0000

Data Index: 89581 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5826. Min Act: -0.0000

Data Index: 673721 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5819. Min Act: -0.0000

Data Index: 332398 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5401. Min Act: -0.0000

Data Index: 136961 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5922. Min Act: -0.0000

Data Index: 217928 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5544. Min Act: -0.0000

Data Index: 669175 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.8537. Min Range: -0.8537

Max Act: 0.5621. Min Act: -0.0000

Data Index: 1031367 (C4 (Web Text))

Max Activating Token Index: 543