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

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

Neuron 3420 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.5707. Min Act: -0.0000

Data Index: 537590 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.5751. Min Act: -0.0000

Data Index: 65925 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4977. Min Act: -0.0000

Data Index: 635264 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1236530 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4703. Min Act: -0.0000

Data Index: 26931 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1335863 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1527871 (Python Code)

Max Activating Token Index: 864

Text #7

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1427919 (Python Code)

Max Activating Token Index: 345

Text #8

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4824. Min Act: -0.0000

Data Index: 1076755 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4803. Min Act: 0.0000

Data Index: 635935 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1042309 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1178574 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4544. Min Act: -0.0000

Data Index: 974726 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1534607 (Python Code)

Max Activating Token Index: 921

Text #14

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.3790. Min Act: 0.0000

Data Index: 1156556 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4323. Min Act: -0.0000

Data Index: 787944 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.3988. Min Act: -0.0000

Data Index: 146239 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4283. Min Act: -0.0000

Data Index: 155550 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4733. Min Act: -0.0000

Data Index: 791210 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.5751. Min Range: -0.5751

Max Act: 0.4108. Min Act: -0.0000

Data Index: 696648 (C4 (Web Text))

Max Activating Token Index: 366