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

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

Neuron 1566 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6022. Min Range: -2.6022

Max Act: 2.6022. Min Act: -0.0000

Data Index: 929666 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 2.6022. Min Range: -2.6022

Max Act: 2.2839. Min Act: -0.0000

Data Index: 252348 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 2.6022. Min Range: -2.6022

Max Act: 2.1418. Min Act: -0.0000

Data Index: 1335307 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 2.6022. Min Range: -2.6022

Max Act: 2.0673. Min Act: -0.0000

Data Index: 752450 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 2.6022. Min Range: -2.6022

Max Act: 1.9916. Min Act: -0.0000

Data Index: 337655 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 2.6022. Min Range: -2.6022

Max Act: 1.8741. Min Act: -0.0000

Data Index: 68129 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 2.6022. Min Range: -2.6022

Max Act: 2.0607. Min Act: -0.0000

Data Index: 1209206 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 2.6022. Min Range: -2.6022

Max Act: 2.0021. Min Act: -0.0000

Data Index: 419294 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 2.6022. Min Range: -2.6022

Max Act: 1.7940. Min Act: -0.0000

Data Index: 693593 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 2.6022. Min Range: -2.6022

Max Act: 1.9823. Min Act: -0.0000

Data Index: 1140382 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 2.6022. Min Range: -2.6022

Max Act: 1.8682. Min Act: -0.0000

Data Index: 1041613 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 2.6022. Min Range: -2.6022

Max Act: 1.8235. Min Act: -0.0000

Data Index: 874293 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 2.6022. Min Range: -2.6022

Max Act: 1.8120. Min Act: -0.0000

Data Index: 174840 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 2.6022. Min Range: -2.6022

Max Act: 1.7796. Min Act: -0.0000

Data Index: 688623 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 2.6022. Min Range: -2.6022

Max Act: 1.8550. Min Act: -0.0000

Data Index: 784955 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 2.6022. Min Range: -2.6022

Max Act: 1.7477. Min Act: -0.0000

Data Index: 388799 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 2.6022. Min Range: -2.6022

Max Act: 1.6394. Min Act: -0.0000

Data Index: 358047 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 2.6022. Min Range: -2.6022

Max Act: 1.6337. Min Act: -0.0000

Data Index: 271261 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 2.6022. Min Range: -2.6022

Max Act: 1.6701. Min Act: -0.0000

Data Index: 502578 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 2.6022. Min Range: -2.6022

Max Act: 1.6010. Min Act: -0.0000

Data Index: 150981 (C4 (Web Text))

Max Activating Token Index: 67