Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5549 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4902. Min Act: -0.0000

Data Index: 342803 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1198784 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4694. Min Act: -0.0000

Data Index: 374756 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4356. Min Act: -0.0000

Data Index: 43039 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3942. Min Act: -0.0000

Data Index: 451388 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4064. Min Act: -0.0000

Data Index: 538022 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4319. Min Act: -0.0000

Data Index: 443313 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3963. Min Act: -0.0000

Data Index: 158735 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3974. Min Act: -0.0000

Data Index: 835223 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4192. Min Act: -0.0000

Data Index: 789046 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4179. Min Act: -0.0000

Data Index: 905984 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3881. Min Act: -0.0000

Data Index: 1510111 (Python Code)

Max Activating Token Index: 96

Text #12

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3834. Min Act: -0.0000

Data Index: 1020325 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3901. Min Act: -0.0000

Data Index: 1260310 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3935. Min Act: -0.0000

Data Index: 478376 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3717. Min Act: -0.0000

Data Index: 586979 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1020207 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3785. Min Act: -0.0000

Data Index: 874603 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3863. Min Act: -0.0000

Data Index: 198388 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3524. Min Act: -0.0000

Data Index: 858583 (C4 (Web Text))

Max Activating Token Index: 642