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

Dataset: The Pile

Neuron 3 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.8079. Min Act: -0.0000

Data Index: 203897 (The Pile)

Max Activating Token Index: 367

Text #1

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1532743 (The Pile)

Max Activating Token Index: 315

Text #2

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1471552 (The Pile)

Max Activating Token Index: 243

Text #3

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.6570. Min Act: -0.0000

Data Index: 313740 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.6252. Min Act: -0.0000

Data Index: 833078 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.6040. Min Act: -0.0000

Data Index: 142564 (The Pile)

Max Activating Token Index: 905

Text #6

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1359585 (The Pile)

Max Activating Token Index: 530

Text #7

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5473. Min Act: -0.0000

Data Index: 435544 (The Pile)

Max Activating Token Index: 714

Text #8

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5844. Min Act: -0.0000

Data Index: 583296 (The Pile)

Max Activating Token Index: 498

Text #9

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5852. Min Act: -0.0000

Data Index: 903013 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.6222. Min Act: -0.0000

Data Index: 797183 (The Pile)

Max Activating Token Index: 767

Text #11

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1079798 (The Pile)

Max Activating Token Index: 263

Text #12

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5767. Min Act: -0.0000

Data Index: 164305 (The Pile)

Max Activating Token Index: 26

Text #13

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5808. Min Act: -0.0000

Data Index: 1864150 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5963. Min Act: -0.0000

Data Index: 639530 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5586. Min Act: -0.0000

Data Index: 1586253 (The Pile)

Max Activating Token Index: 489

Text #16

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.6336. Min Act: -0.0000

Data Index: 990925 (The Pile)

Max Activating Token Index: 826

Text #17

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5206. Min Act: -0.0000

Data Index: 795370 (The Pile)

Max Activating Token Index: 774

Text #18

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5425. Min Act: -0.0000

Data Index: 670326 (The Pile)

Max Activating Token Index: 685

Text #19

Max Range: 0.8079. Min Range: -0.8079

Max Act: 0.5537. Min Act: -0.0000

Data Index: 475167 (The Pile)

Max Activating Token Index: 848