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

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

Neuron 2657 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.3644. Min Act: -0.0000

Data Index: 823451 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 1.3644. Min Range: -1.3644

Max Act: 1.0788. Min Act: -0.0000

Data Index: 160009 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.9930. Min Act: -0.0000

Data Index: 251057 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.9265. Min Act: -0.0000

Data Index: 69742 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.9229. Min Act: -0.0000

Data Index: 1333422 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.9189. Min Act: -0.0000

Data Index: 889768 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.9298. Min Act: -0.0000

Data Index: 640314 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1099446 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.8162. Min Act: -0.0000

Data Index: 878368 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1139361 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.8175. Min Act: -0.0000

Data Index: 676447 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.8111. Min Act: -0.0000

Data Index: 947157 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1172789 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.8577. Min Act: -0.0000

Data Index: 608030 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.7999. Min Act: -0.0000

Data Index: 635393 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.7718. Min Act: -0.0000

Data Index: 662653 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.7994. Min Act: -0.0000

Data Index: 847660 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.7988. Min Act: -0.0000

Data Index: 64825 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.8202. Min Act: -0.0000

Data Index: 331078 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 1.3644. Min Range: -1.3644

Max Act: 0.7969. Min Act: -0.0000

Data Index: 740649 (C4 (Web Text))

Max Activating Token Index: 5