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

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

Neuron 1169 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: 0.3593. Min Range: -0.3593

Max Act: 0.3593. Min Act: -0.0001

Data Index: 104223 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3311. Min Act: -0.0001

Data Index: 908626 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3561. Min Act: -0.0001

Data Index: 711705 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3293. Min Act: -0.0001

Data Index: 247320 (C4 (Web Text))

Max Activating Token Index: 481

Text #4

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3111. Min Act: -0.0001

Data Index: 64143 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3171. Min Act: -0.0001

Data Index: 599923 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3080. Min Act: -0.0001

Data Index: 749417 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3169. Min Act: -0.0001

Data Index: 22424 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2960. Min Act: -0.0001

Data Index: 850703 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2935. Min Act: -0.0001

Data Index: 550989 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.3069. Min Act: -0.0001

Data Index: 1158613 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2702. Min Act: -0.0001

Data Index: 1227463 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2406. Min Act: -0.0001

Data Index: 1352528 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2846. Min Act: -0.0001

Data Index: 837000 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2600. Min Act: -0.0001

Data Index: 483516 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2840. Min Act: -0.0001

Data Index: 634768 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2736. Min Act: -0.0001

Data Index: 327993 (C4 (Web Text))

Max Activating Token Index: 523

Text #17

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2609. Min Act: -0.0001

Data Index: 880703 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2581. Min Act: -0.0001

Data Index: 274710 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 0.3593. Min Range: -0.3593

Max Act: 0.2758. Min Act: -0.0001

Data Index: 616127 (C4 (Web Text))

Max Activating Token Index: 898