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

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

Neuron 1593 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.4919. Min Act: -0.0000

Data Index: 902163 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.4754. Min Act: -0.0000

Data Index: 81435 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.4576. Min Act: -0.0000

Data Index: 17061 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.4681. Min Act: -0.0000

Data Index: 1107666 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.4529. Min Act: -0.0000

Data Index: 163740 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.4261. Min Act: -0.0000

Data Index: 888372 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.4283. Min Act: -0.0000

Data Index: 395311 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.4081. Min Act: -0.0000

Data Index: 677275 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.4114. Min Act: -0.0000

Data Index: 75133 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3962. Min Act: -0.0000

Data Index: 688793 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3913. Min Act: -0.0000

Data Index: 1222000 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1318925 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3849. Min Act: -0.0000

Data Index: 942260 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3782. Min Act: -0.0000

Data Index: 1004948 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3793. Min Act: -0.0000

Data Index: 126838 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3893. Min Act: 0.0000

Data Index: 1221294 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3861. Min Act: -0.0000

Data Index: 7611 (C4 (Web Text))

Max Activating Token Index: 252

Text #17

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1127684 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3813. Min Act: -0.0000

Data Index: 767171 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.4919. Min Range: -0.4919

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1228029 (C4 (Web Text))

Max Activating Token Index: 267