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

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

Neuron 3083 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.2037. Min Act: -0.0000

Data Index: 246178 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.2477. Min Act: -0.0000

Data Index: 420926 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.2662. Min Act: -0.0000

Data Index: 1126577 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.1419. Min Act: -0.0000

Data Index: 170509 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.2144. Min Act: -0.0000

Data Index: 304458 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.1962. Min Act: -0.0000

Data Index: 804507 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.0860. Min Act: -0.0000

Data Index: 307535 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.1471. Min Act: -0.0000

Data Index: 68698 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.1130. Min Act: -0.0000

Data Index: 69150 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.0612. Min Act: -0.0000

Data Index: 1022498 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.0320. Min Act: -0.0000

Data Index: 755980 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.0626. Min Act: -0.0000

Data Index: 54879 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.0143. Min Act: -0.0000

Data Index: 230223 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.0500. Min Act: -0.0000

Data Index: 1068146 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 1.2662. Min Range: -1.2662

Max Act: 0.9877. Min Act: -0.0000

Data Index: 494071 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 1.2662. Min Range: -1.2662

Max Act: 0.9778. Min Act: -0.0000

Data Index: 699340 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 1.2662. Min Range: -1.2662

Max Act: 0.9810. Min Act: -0.0000

Data Index: 855047 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.0081. Min Act: -0.0000

Data Index: 114196 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 1.2662. Min Range: -1.2662

Max Act: 1.0003. Min Act: -0.0000

Data Index: 100602 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 1.2662. Min Range: -1.2662

Max Act: 0.9915. Min Act: -0.0000

Data Index: 174573 (C4 (Web Text))

Max Activating Token Index: 451