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

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

Neuron 4208 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0893. Min Range: -1.0893

Max Act: 1.0893. Min Act: -0.0000

Data Index: 207473 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9945. Min Act: -0.0000

Data Index: 21048 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 1.0893. Min Range: -1.0893

Max Act: 1.0435. Min Act: -0.0000

Data Index: 1255587 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 1.0893. Min Range: -1.0893

Max Act: 1.0173. Min Act: -0.0000

Data Index: 409464 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9756. Min Act: -0.0000

Data Index: 846748 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 1.0893. Min Range: -1.0893

Max Act: 1.0049. Min Act: -0.0000

Data Index: 1046938 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9944. Min Act: -0.0000

Data Index: 687920 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9216. Min Act: -0.0000

Data Index: 47591 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9115. Min Act: -0.0000

Data Index: 852399 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9577. Min Act: -0.0000

Data Index: 629367 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9288. Min Act: -0.0000

Data Index: 115218 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9143. Min Act: -0.0000

Data Index: 537890 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8943. Min Act: -0.0000

Data Index: 303732 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8814. Min Act: -0.0000

Data Index: 129131 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8983. Min Act: -0.0000

Data Index: 265615 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8966. Min Act: -0.0001

Data Index: 622884 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8930. Min Act: -0.0000

Data Index: 461913 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9451. Min Act: -0.0000

Data Index: 825533 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8909. Min Act: -0.0000

Data Index: 1079657 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8870. Min Act: -0.0000

Data Index: 858406 (C4 (Web Text))

Max Activating Token Index: 701