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

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

Neuron 1571 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.8647. Min Act: -0.0000

Data Index: 398481 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.8584. Min Act: -0.0000

Data Index: 927649 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1067422 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.8403. Min Act: -0.0000

Data Index: 784105 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7909. Min Act: -0.0000

Data Index: 15649 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1000907 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7947. Min Act: -0.0000

Data Index: 791664 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.8005. Min Act: -0.0000

Data Index: 177999 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7422. Min Act: -0.0000

Data Index: 873810 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7024. Min Act: -0.0000

Data Index: 1113290 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1601789 (Python Code)

Max Activating Token Index: 317

Text #11

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1514957 (Python Code)

Max Activating Token Index: 845

Text #12

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7180. Min Act: -0.0000

Data Index: 1084723 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1104571 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7157. Min Act: -0.0000

Data Index: 34535 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1076141 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7064. Min Act: -0.0000

Data Index: 359774 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7454. Min Act: -0.0000

Data Index: 78499 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1343234 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.8647. Min Range: -0.8647

Max Act: 0.7151. Min Act: -0.0000

Data Index: 29329 (C4 (Web Text))

Max Activating Token Index: 43