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

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

Neuron 2187 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: 0.8902. Min Range: -0.8902

Max Act: 0.8902. Min Act: -0.0002

Data Index: 338048 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.7334. Min Act: -0.0002

Data Index: 27045 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6981. Min Act: -0.0001

Data Index: 777119 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6581. Min Act: -0.0002

Data Index: 965036 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.5989. Min Act: -0.0002

Data Index: 46244 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6502. Min Act: -0.0002

Data Index: 606895 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6238. Min Act: -0.0002

Data Index: 17617 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6400. Min Act: -0.0002

Data Index: 202786 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6223. Min Act: -0.0002

Data Index: 375485 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.5754. Min Act: -0.0002

Data Index: 1294997 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.5873. Min Act: -0.0002

Data Index: 1129166 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.5888. Min Act: -0.0002

Data Index: 575179 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.6011. Min Act: -0.0002

Data Index: 63753 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.5659. Min Act: -0.0001

Data Index: 1324819 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.5645. Min Act: -0.0002

Data Index: 840691 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.5616. Min Act: -0.0002

Data Index: 87499 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.5788. Min Act: -0.0002

Data Index: 851896 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.5531. Min Act: -0.0002

Data Index: 6650 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.5520. Min Act: -0.0002

Data Index: 565714 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.8902. Min Range: -0.8902

Max Act: 0.5642. Min Act: -0.0002

Data Index: 1333962 (C4 (Web Text))

Max Activating Token Index: 618