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

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

Neuron 1797 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.7529. Min Act: -0.0000

Data Index: 558557 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.6880. Min Act: -0.0000

Data Index: 188546 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.6652. Min Act: -0.0000

Data Index: 297044 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.6604. Min Act: -0.0000

Data Index: 298006 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1115625 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.6353. Min Act: 0.0000

Data Index: 305511 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.6270. Min Act: -0.0000

Data Index: 48679 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1222674 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.6142. Min Act: -0.0000

Data Index: 945055 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.6134. Min Act: 0.0000

Data Index: 682535 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.5937. Min Act: -0.0000

Data Index: 847211 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.5786. Min Act: -0.0000

Data Index: 118752 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.6183. Min Act: -0.0000

Data Index: 453573 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1304038 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.5884. Min Act: -0.0000

Data Index: 574483 (C4 (Web Text))

Max Activating Token Index: 998

Text #15

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1181949 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.5874. Min Act: 0.0000

Data Index: 665972 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.5695. Min Act: -0.0000

Data Index: 1121494 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.5897. Min Act: -0.0000

Data Index: 908534 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.7529. Min Range: -0.7529

Max Act: 0.5718. Min Act: -0.0000

Data Index: 584701 (C4 (Web Text))

Max Activating Token Index: 279