Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 66 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1696. Min Range: -1.1696

Max Act: 1.1696. Min Act: -0.0000

Data Index: 1141867 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 1.1696. Min Range: -1.1696

Max Act: 1.1629. Min Act: -0.0000

Data Index: 153508 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 1.1696. Min Range: -1.1696

Max Act: 1.0472. Min Act: -0.0000

Data Index: 700346 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.9508. Min Act: -0.0000

Data Index: 439417 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.9958. Min Act: -0.0000

Data Index: 909720 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.9432. Min Act: -0.0000

Data Index: 312456 (C4 (Web Text))

Max Activating Token Index: 67

Text #6

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.9946. Min Act: -0.0000

Data Index: 966975 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.9192. Min Act: -0.0000

Data Index: 348844 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.9563. Min Act: -0.0000

Data Index: 98384 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1295927 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.9446. Min Act: -0.0000

Data Index: 969073 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.8969. Min Act: -0.0000

Data Index: 900476 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.9517. Min Act: -0.0000

Data Index: 106288 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.9540. Min Act: -0.0000

Data Index: 417438 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.9083. Min Act: -0.0000

Data Index: 1232060 (C4 (Web Text))

Max Activating Token Index: 465

Text #15

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.9125. Min Act: -0.0000

Data Index: 61947 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.8697. Min Act: -0.0000

Data Index: 591938 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.9421. Min Act: -0.0000

Data Index: 1246982 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.8790. Min Act: -0.0000

Data Index: 53435 (C4 (Web Text))

Max Activating Token Index: 645

Text #19

Max Range: 1.1696. Min Range: -1.1696

Max Act: 0.8719. Min Act: -0.0000

Data Index: 186254 (C4 (Web Text))

Max Activating Token Index: 100