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

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

Neuron 5073 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.9635. Min Act: -0.0000

Data Index: 1103387 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.7531. Min Act: -0.0000

Data Index: 225348 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.8255. Min Act: -0.0000

Data Index: 648898 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.4657. Min Act: -0.0000

Data Index: 207275 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 1.9635. Min Range: -1.9635

Max Act: 0.9778. Min Act: -0.0000

Data Index: 686680 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 1.9635. Min Range: -1.9635

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1241769 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.9635. Min Range: -1.9635

Max Act: 0.8161. Min Act: -0.0000

Data Index: 1326997 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 1.9635. Min Range: -1.9635

Max Act: 0.7556. Min Act: -0.0000

Data Index: 6432 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 1.9635. Min Range: -1.9635

Max Act: 0.7027. Min Act: -0.0000

Data Index: 457599 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 1.9635. Min Range: -1.9635

Max Act: 0.6391. Min Act: -0.0000

Data Index: 504214 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.9635. Min Range: -1.9635

Max Act: 0.6111. Min Act: -0.0000

Data Index: 605030 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 1.9635. Min Range: -1.9635

Max Act: 0.6060. Min Act: -0.0000

Data Index: 275820 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 1.9635. Min Range: -1.9635

Max Act: 0.6058. Min Act: -0.0000

Data Index: 377047 (C4 (Web Text))

Max Activating Token Index: 374

Text #13

Max Range: 1.9635. Min Range: -1.9635

Max Act: 0.5495. Min Act: -0.0000

Data Index: 438491 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 1.9635. Min Range: -1.9635

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1160028 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 1.9635. Min Range: -1.9635

Max Act: 0.4284. Min Act: -0.0000

Data Index: 813903 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 1.9635. Min Range: -1.9635

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1152201 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 1.9635. Min Range: -1.9635

Max Act: 0.4961. Min Act: -0.0000

Data Index: 20661 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 1.9635. Min Range: -1.9635

Max Act: 0.5164. Min Act: -0.0000

Data Index: 107131 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 1.9635. Min Range: -1.9635

Max Act: 0.4880. Min Act: -0.0000

Data Index: 565191 (C4 (Web Text))

Max Activating Token Index: 147