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

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

Neuron 3550 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7771. Min Range: -3.7771

Max Act: 3.7771. Min Act: -0.0001

Data Index: 1256090 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 3.7771. Min Range: -3.7771

Max Act: 3.3375. Min Act: -0.0000

Data Index: 3967 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 3.7771. Min Range: -3.7771

Max Act: 3.7605. Min Act: -0.0001

Data Index: 1104323 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 3.7771. Min Range: -3.7771

Max Act: 3.0940. Min Act: -0.0001

Data Index: 1091019 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 3.7771. Min Range: -3.7771

Max Act: 3.0234. Min Act: -0.0001

Data Index: 360267 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 3.7771. Min Range: -3.7771

Max Act: 3.0208. Min Act: -0.0001

Data Index: 640029 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.7886. Min Act: -0.0001

Data Index: 465600 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.9076. Min Act: -0.0001

Data Index: 1291598 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 3.7771. Min Range: -3.7771

Max Act: 3.0026. Min Act: -0.0000

Data Index: 689521 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.8801. Min Act: -0.0000

Data Index: 993137 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.7203. Min Act: -0.0001

Data Index: 165310 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.6919. Min Act: -0.0001

Data Index: 1346267 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.6192. Min Act: -0.0000

Data Index: 33245 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.6256. Min Act: -0.0001

Data Index: 75321 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.4655. Min Act: -0.0001

Data Index: 240467 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.4628. Min Act: -0.0001

Data Index: 726132 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.5778. Min Act: -0.0001

Data Index: 738100 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.6861. Min Act: -0.0001

Data Index: 1195223 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.4330. Min Act: -0.0001

Data Index: 1038902 (C4 (Web Text))

Max Activating Token Index: 897

Text #19

Max Range: 3.7771. Min Range: -3.7771

Max Act: 2.4269. Min Act: -0.0001

Data Index: 600880 (C4 (Web Text))

Max Activating Token Index: 599