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

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

Neuron 3641 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1293750 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1348753 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0589. Min Act: -0.0002

Data Index: 204769 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0575. Min Act: -0.0002

Data Index: 991109 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0581. Min Act: -0.0002

Data Index: 399579 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0593. Min Act: -0.0002

Data Index: 3213 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1676 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0583. Min Act: -0.0002

Data Index: 749648 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0569. Min Act: -0.0002

Data Index: 898667 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0560. Min Act: -0.0002

Data Index: 346553 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0565. Min Act: -0.0002

Data Index: 836205 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0551. Min Act: -0.0002

Data Index: 567467 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0536. Min Act: -0.0002

Data Index: 532618 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1204570 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1174145 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0530. Min Act: -0.0002

Data Index: 950133 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0546. Min Act: -0.0002

Data Index: 111310 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0533. Min Act: -0.0002

Data Index: 762155 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0542. Min Act: -0.0002

Data Index: 863097 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.0788. Min Range: -0.0788

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1253966 (C4 (Web Text))

Max Activating Token Index: 308