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

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

Neuron 3791 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: 0.6951. Min Range: -0.6951

Max Act: 0.6951. Min Act: -0.0000

Data Index: 892032 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6573. Min Act: -0.0000

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 381

Text #2

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6029. Min Act: -0.0000

Data Index: 936143 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6110. Min Act: 0.0000

Data Index: 745015 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6009. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.6042. Min Act: -0.0000

Data Index: 27456 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5780. Min Act: 0.0000

Data Index: 385968 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5841. Min Act: -0.0000

Data Index: 475232 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5924. Min Act: -0.0000

Data Index: 681912 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5511. Min Act: -0.0000

Data Index: 334372 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5425. Min Act: -0.0000

Data Index: 967533 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5267. Min Act: -0.0000

Data Index: 448981 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5135. Min Act: 0.0000

Data Index: 1278665 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1063934 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4988. Min Act: 0.0000

Data Index: 1041258 (C4 (Web Text))

Max Activating Token Index: 876

Text #15

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4811. Min Act: -0.0000

Data Index: 482919 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4684. Min Act: -0.0000

Data Index: 254688 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4550. Min Act: -0.0000

Data Index: 830590 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4655. Min Act: -0.0000

Data Index: 597903 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.6951. Min Range: -0.6951

Max Act: 0.4636. Min Act: -0.0000

Data Index: 101753 (C4 (Web Text))

Max Activating Token Index: 271