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

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

Neuron 507 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1046407 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0583. Min Act: -0.0002

Data Index: 976424 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0573. Min Act: -0.0002

Data Index: 487330 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0561. Min Act: -0.0002

Data Index: 644751 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0561. Min Act: -0.0002

Data Index: 101018 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0544. Min Act: -0.0002

Data Index: 792475 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0528. Min Act: -0.0002

Data Index: 673221 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1284273 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1106680 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0518. Min Act: -0.0003

Data Index: 693848 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0514. Min Act: -0.0002

Data Index: 714245 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0516. Min Act: -0.0002

Data Index: 392787 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0507. Min Act: -0.0002

Data Index: 535303 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1150719 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0509. Min Act: -0.0002

Data Index: 476600 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0492. Min Act: -0.0002

Data Index: 566172 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0494. Min Act: -0.0002

Data Index: 861938 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0499. Min Act: -0.0002

Data Index: 307478 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0491. Min Act: -0.0002

Data Index: 713581 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.0609. Min Range: -0.0609

Max Act: 0.0495. Min Act: -0.0002

Data Index: 242806 (C4 (Web Text))

Max Activating Token Index: 113