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

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

Neuron 4902 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: 1.3112. Min Range: -1.3112

Max Act: 1.3112. Min Act: -0.0000

Data Index: 9116 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.1906. Min Act: -0.0000

Data Index: 480706 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 1.3112. Min Range: -1.3112

Max Act: 0.9597. Min Act: -0.0000

Data Index: 364164 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 1.3112. Min Range: -1.3112

Max Act: 0.9877. Min Act: -0.0000

Data Index: 1056669 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.0386. Min Act: -0.0000

Data Index: 1354741 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 1.3112. Min Range: -1.3112

Max Act: 0.8360. Min Act: -0.0000

Data Index: 443261 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.0378. Min Act: -0.0000

Data Index: 764270 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 1.3112. Min Range: -1.3112

Max Act: 1.0226. Min Act: -0.0000

Data Index: 68483 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 1.3112. Min Range: -1.3112

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1226386 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 1.3112. Min Range: -1.3112

Max Act: 0.9867. Min Act: -0.0000

Data Index: 1250934 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 1.3112. Min Range: -1.3112

Max Act: 0.9810. Min Act: -0.0000

Data Index: 1267064 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 1.3112. Min Range: -1.3112

Max Act: 0.9728. Min Act: -0.0000

Data Index: 199710 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 1.3112. Min Range: -1.3112

Max Act: 0.9886. Min Act: -0.0000

Data Index: 1355115 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 1.3112. Min Range: -1.3112

Max Act: 0.8516. Min Act: -0.0000

Data Index: 444663 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 1.3112. Min Range: -1.3112

Max Act: 0.8987. Min Act: -0.0000

Data Index: 635361 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 1.3112. Min Range: -1.3112

Max Act: 0.8660. Min Act: -0.0000

Data Index: 619608 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 1.3112. Min Range: -1.3112

Max Act: 0.8984. Min Act: -0.0000

Data Index: 529508 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 1.3112. Min Range: -1.3112

Max Act: 0.9491. Min Act: -0.0000

Data Index: 315222 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 1.3112. Min Range: -1.3112

Max Act: 0.9172. Min Act: -0.0000

Data Index: 419112 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 1.3112. Min Range: -1.3112

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1315950 (C4 (Web Text))

Max Activating Token Index: 833