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

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

Neuron 2652 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.9068. Min Act: -0.0000

Data Index: 245896 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.8690. Min Act: -0.0001

Data Index: 1289062 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.8938. Min Act: -0.0001

Data Index: 1312174 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.8762. Min Act: -0.0001

Data Index: 970465 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.8226. Min Act: -0.0001

Data Index: 1002797 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.8779. Min Act: -0.0001

Data Index: 1119283 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7609. Min Act: -0.0001

Data Index: 235146 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7489. Min Act: -0.0001

Data Index: 802149 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7894. Min Act: -0.0001

Data Index: 397427 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.8127. Min Act: -0.0001

Data Index: 1169629 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7572. Min Act: -0.0001

Data Index: 1144649 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7710. Min Act: -0.0001

Data Index: 1281525 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7645. Min Act: -0.0001

Data Index: 971636 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7690. Min Act: -0.0000

Data Index: 123983 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7926. Min Act: -0.0001

Data Index: 768688 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7720. Min Act: -0.0001

Data Index: 1616267 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7673. Min Act: -0.0001

Data Index: 318014 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7952. Min Act: -0.0001

Data Index: 1539103 (Python Code)

Max Activating Token Index: 334

Text #18

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1177728 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.9068. Min Range: -0.9068

Max Act: 0.7884. Min Act: -0.0001

Data Index: 629788 (C4 (Web Text))

Max Activating Token Index: 34