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

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

Neuron 484 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.6242. Min Act: -0.0000

Data Index: 125393 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.6288. Min Act: -0.0000

Data Index: 791004 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.5570. Min Act: -0.0000

Data Index: 1032651 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.6328. Min Act: -0.0000

Data Index: 535942 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.4445. Min Act: -0.0000

Data Index: 638769 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.3192. Min Act: -0.0000

Data Index: 211884 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.3139. Min Act: -0.0001

Data Index: 1155128 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.1546. Min Act: -0.0000

Data Index: 904678 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.0946. Min Act: -0.0000

Data Index: 1067034 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.1621. Min Act: -0.0000

Data Index: 605846 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.1634. Min Act: -0.0000

Data Index: 1213242 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.1097. Min Act: -0.0000

Data Index: 156641 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.0595. Min Act: -0.0000

Data Index: 47556 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.0531. Min Act: -0.0000

Data Index: 164326 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.0838. Min Act: -0.0000

Data Index: 606022 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 2.6328. Min Range: -2.6328

Max Act: 1.9923. Min Act: -0.0000

Data Index: 560145 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.0539. Min Act: -0.0000

Data Index: 1282477 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 2.6328. Min Range: -2.6328

Max Act: 1.9487. Min Act: -0.0000

Data Index: 51250 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 2.6328. Min Range: -2.6328

Max Act: 1.9504. Min Act: -0.0000

Data Index: 857229 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 2.6328. Min Range: -2.6328

Max Act: 2.0126. Min Act: -0.0001

Data Index: 1175854 (C4 (Web Text))

Max Activating Token Index: 337