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

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

Neuron 256 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: 1.0578. Min Range: -1.0578

Max Act: 1.0578. Min Act: 0.0000

Data Index: 1121037 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.9920. Min Act: -0.0000

Data Index: 568151 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.9786. Min Act: -0.0000

Data Index: 296976 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.9288. Min Act: -0.0000

Data Index: 111607 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.9207. Min Act: -0.0000

Data Index: 1248815 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.9071. Min Act: -0.0000

Data Index: 1343549 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.8306. Min Act: -0.0000

Data Index: 423048 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.8571. Min Act: -0.0000

Data Index: 11585 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.8438. Min Act: -0.0000

Data Index: 1175580 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.8307. Min Act: -0.0000

Data Index: 356602 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.8300. Min Act: -0.0000

Data Index: 26999 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.8154. Min Act: -0.0000

Data Index: 703621 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.8101. Min Act: -0.0000

Data Index: 611246 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7563. Min Act: -0.0000

Data Index: 399260 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7642. Min Act: 0.0000

Data Index: 332925 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.8391. Min Act: -0.0000

Data Index: 949818 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7657. Min Act: -0.0000

Data Index: 106436 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7636. Min Act: -0.0000

Data Index: 143155 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7641. Min Act: -0.0000

Data Index: 210055 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 1.0578. Min Range: -1.0578

Max Act: 0.7425. Min Act: -0.0000

Data Index: 166586 (C4 (Web Text))

Max Activating Token Index: 104