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

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

Neuron 437 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.6548. Min Act: -0.0000

Data Index: 229146 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.6365. Min Act: -0.0000

Data Index: 809937 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5846. Min Act: -0.0000

Data Index: 635038 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5846. Min Act: -0.0000

Data Index: 737081 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1217868 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.5333. Min Act: -0.0000

Data Index: 96813 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4638. Min Act: -0.0000

Data Index: 621084 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4565. Min Act: -0.0000

Data Index: 888830 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4684. Min Act: -0.0000

Data Index: 726551 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4816. Min Act: -0.0000

Data Index: 720805 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4685. Min Act: 0.0000

Data Index: 156900 (C4 (Web Text))

Max Activating Token Index: 257

Text #11

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1138178 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4443. Min Act: -0.0000

Data Index: 501787 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4397. Min Act: -0.0000

Data Index: 592407 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4333. Min Act: -0.0000

Data Index: 961891 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4451. Min Act: -0.0000

Data Index: 442380 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4164. Min Act: -0.0000

Data Index: 719975 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4260. Min Act: -0.0000

Data Index: 750886 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.4055. Min Act: -0.0000

Data Index: 60010 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.6548. Min Range: -0.6548

Max Act: 0.3936. Min Act: -0.0000

Data Index: 809108 (C4 (Web Text))

Max Activating Token Index: 315