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

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

Neuron 5540 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.9589. Min Act: -0.0000

Data Index: 912258 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.5095. Min Act: -0.0000

Data Index: 832318 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.4262. Min Act: -0.0000

Data Index: 413624 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.3678. Min Act: -0.0000

Data Index: 66228 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.3235. Min Act: -0.0000

Data Index: 441952 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.3521. Min Act: -0.0000

Data Index: 1343197 (C4 (Web Text))

Max Activating Token Index: 161

Text #6

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.2471. Min Act: -0.0000

Data Index: 771550 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.3569. Min Act: -0.0000

Data Index: 128306 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.3490. Min Act: -0.0000

Data Index: 321838 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.1992. Min Act: -0.0000

Data Index: 1282681 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.2510. Min Act: -0.0000

Data Index: 1121921 (C4 (Web Text))

Max Activating Token Index: 945

Text #11

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.2499. Min Act: -0.0000

Data Index: 279542 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.2499. Min Act: -0.0000

Data Index: 1088950 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.2600. Min Act: -0.0000

Data Index: 650945 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.1808. Min Act: -0.0000

Data Index: 919239 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.1051. Min Act: -0.0000

Data Index: 644881 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.1153. Min Act: -0.0000

Data Index: 159022 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.1489. Min Act: -0.0000

Data Index: 488318 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.3101. Min Act: -0.0000

Data Index: 788436 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 1.9589. Min Range: -1.9589

Max Act: 1.1844. Min Act: -0.0000

Data Index: 904289 (C4 (Web Text))

Max Activating Token Index: 675