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

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

Neuron 2614 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.7249. Min Act: -0.0001

Data Index: 1254974 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.7505. Min Act: -0.0001

Data Index: 404426 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.4338. Min Act: -0.0001

Data Index: 1134107 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.3831. Min Act: -0.0001

Data Index: 908612 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.4025. Min Act: -0.0001

Data Index: 823993 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.3125. Min Act: -0.0001

Data Index: 93661 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.1925. Min Act: -0.0001

Data Index: 1033553 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.4178. Min Act: -0.0001

Data Index: 790874 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.3292. Min Act: -0.0001

Data Index: 652662 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.2964. Min Act: -0.0001

Data Index: 750292 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.2127. Min Act: -0.0001

Data Index: 10396 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.2896. Min Act: -0.0001

Data Index: 155927 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.2940. Min Act: -0.0001

Data Index: 673718 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.1782. Min Act: -0.0001

Data Index: 589611 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.2578. Min Act: -0.0001

Data Index: 1031465 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.2462. Min Act: -0.0001

Data Index: 528662 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.1928. Min Act: -0.0001

Data Index: 446659 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.2126. Min Act: -0.0001

Data Index: 37589 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.2277. Min Act: -0.0001

Data Index: 24473 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.7505. Min Range: -1.7505

Max Act: 1.2966. Min Act: -0.0001

Data Index: 244526 (C4 (Web Text))

Max Activating Token Index: 747