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

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

Neuron 4690 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.8726. Min Act: 0.0000

Data Index: 155639 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7975. Min Act: -0.0000

Data Index: 599319 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7807. Min Act: -0.0000

Data Index: 231480 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7591. Min Act: -0.0000

Data Index: 434374 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.8111. Min Act: -0.0000

Data Index: 995959 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.8090. Min Act: -0.0000

Data Index: 641609 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.8008. Min Act: -0.0000

Data Index: 813717 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7963. Min Act: -0.0000

Data Index: 968828 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7882. Min Act: -0.0000

Data Index: 871098 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7902. Min Act: 0.0000

Data Index: 408630 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7888. Min Act: -0.0000

Data Index: 976231 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7867. Min Act: -0.0000

Data Index: 183579 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7821. Min Act: -0.0000

Data Index: 1010382 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7309. Min Act: -0.0000

Data Index: 1273582 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7700. Min Act: -0.0000

Data Index: 1347795 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7225. Min Act: -0.0000

Data Index: 917740 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7707. Min Act: -0.0000

Data Index: 360897 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7208. Min Act: -0.0000

Data Index: 336170 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7621. Min Act: 0.0000

Data Index: 170062 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.8726. Min Range: -0.8726

Max Act: 0.7647. Min Act: -0.0000

Data Index: 905850 (C4 (Web Text))

Max Activating Token Index: 298