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

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

Neuron 2570 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: 0.3598. Min Range: -0.3598

Max Act: 0.3598. Min Act: 0.0000

Data Index: 966513 (C4 (Web Text))

Max Activating Token Index: 486

Text #1

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1104397 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3095. Min Act: -0.0000

Data Index: 865199 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3233. Min Act: -0.0000

Data Index: 562573 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3099. Min Act: -0.0000

Data Index: 190512 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3085. Min Act: -0.0000

Data Index: 35949 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3009. Min Act: 0.0000

Data Index: 727497 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3003. Min Act: -0.0000

Data Index: 1358101 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2879. Min Act: -0.0000

Data Index: 278810 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3035. Min Act: -0.0000

Data Index: 39806 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1328736 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2814. Min Act: -0.0000

Data Index: 661993 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1017419 (C4 (Web Text))

Max Activating Token Index: 876

Text #13

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1117118 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2848. Min Act: -0.0000

Data Index: 9155 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1320264 (C4 (Web Text))

Max Activating Token Index: 710

Text #16

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2672. Min Act: -0.0000

Data Index: 133928 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1297727 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2746. Min Act: -0.0000

Data Index: 1245012 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 0.3598. Min Range: -0.3598

Max Act: 0.2562. Min Act: -0.0000

Data Index: 589587 (C4 (Web Text))

Max Activating Token Index: 591