Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1431 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0917. Min Act: -0.0003

Data Index: 718869 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0905. Min Act: -0.0003

Data Index: 777616 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0793. Min Act: -0.0003

Data Index: 318700 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0815. Min Act: -0.0003

Data Index: 1237218 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0769. Min Act: -0.0003

Data Index: 1119463 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0746. Min Act: -0.0003

Data Index: 1186086 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0798. Min Act: -0.0003

Data Index: 132361 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0772. Min Act: -0.0003

Data Index: 637264 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0771. Min Act: -0.0003

Data Index: 401387 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0744. Min Act: -0.0003

Data Index: 222421 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0746. Min Act: -0.0003

Data Index: 1107936 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0734. Min Act: -0.0004

Data Index: 650091 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0729. Min Act: -0.0003

Data Index: 599163 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0689. Min Act: -0.0003

Data Index: 1465539 (Python Code)

Max Activating Token Index: 328

Text #14

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0700. Min Act: -0.0003

Data Index: 1074499 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0712. Min Act: -0.0003

Data Index: 339780 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0713. Min Act: -0.0003

Data Index: 840641 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0709. Min Act: -0.0003

Data Index: 469843 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0709. Min Act: -0.0004

Data Index: 803233 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.0917. Min Range: -0.0917

Max Act: 0.0709. Min Act: -0.0003

Data Index: 543124 (C4 (Web Text))

Max Activating Token Index: 484