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

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

Neuron 3053 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0646. Min Range: -3.0646

Max Act: 3.0295. Min Act: -0.0000

Data Index: 1310479 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.9256. Min Act: -0.0000

Data Index: 59789 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 3.0646. Min Range: -3.0646

Max Act: 3.0646. Min Act: -0.0000

Data Index: 224868 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.7449. Min Act: -0.0000

Data Index: 418049 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.8917. Min Act: -0.0000

Data Index: 11182 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 3.0646. Min Range: -3.0646

Max Act: 3.0363. Min Act: -0.0000

Data Index: 53636 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.8811. Min Act: -0.0000

Data Index: 313188 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.9503. Min Act: -0.0000

Data Index: 618091 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.6071. Min Act: -0.0000

Data Index: 1005097 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.7325. Min Act: -0.0000

Data Index: 1211691 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.8751. Min Act: -0.0000

Data Index: 435088 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.6937. Min Act: -0.0000

Data Index: 939253 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.8394. Min Act: -0.0000

Data Index: 735941 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.6692. Min Act: -0.0000

Data Index: 463996 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.4986. Min Act: -0.0000

Data Index: 878951 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 3.0646. Min Range: -3.0646

Max Act: 3.0507. Min Act: -0.0000

Data Index: 1248262 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.7599. Min Act: -0.0000

Data Index: 720259 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.7330. Min Act: -0.0000

Data Index: 883668 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.6964. Min Act: -0.0000

Data Index: 469371 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 3.0646. Min Range: -3.0646

Max Act: 2.4826. Min Act: -0.0000

Data Index: 531956 (C4 (Web Text))

Max Activating Token Index: 248