Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4036 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4217. Min Range: -1.4217

Max Act: 1.4217. Min Act: -0.0001

Data Index: 650177 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.9792. Min Act: -0.0001

Data Index: 1239094 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8770. Min Act: -0.0001

Data Index: 267376 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.9517. Min Act: -0.0001

Data Index: 570239 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.9046. Min Act: -0.0001

Data Index: 1235782 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8269. Min Act: -0.0001

Data Index: 704744 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.7580. Min Act: -0.0001

Data Index: 652692 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8738. Min Act: -0.0001

Data Index: 1231853 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8696. Min Act: -0.0001

Data Index: 1026235 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8466. Min Act: -0.0001

Data Index: 1084868 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8632. Min Act: -0.0001

Data Index: 199579 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8321. Min Act: -0.0001

Data Index: 912077 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8023. Min Act: -0.0001

Data Index: 1254943 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8965. Min Act: -0.0001

Data Index: 1158352 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8452. Min Act: -0.0001

Data Index: 256651 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.7833. Min Act: -0.0001

Data Index: 1248400 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.7980. Min Act: -0.0001

Data Index: 26887 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.8258. Min Act: -0.0001

Data Index: 438726 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.7899. Min Act: -0.0001

Data Index: 1300426 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 1.4217. Min Range: -1.4217

Max Act: 0.7627. Min Act: -0.0001

Data Index: 401164 (C4 (Web Text))

Max Activating Token Index: 46