Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1645 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2380. Min Act: -0.0001

Data Index: 189649 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2449. Min Act: -0.0001

Data Index: 594059 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2344. Min Act: -0.0001

Data Index: 491251 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2181. Min Act: -0.0001

Data Index: 757603 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1990. Min Act: -0.0001

Data Index: 875713 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2077. Min Act: -0.0001

Data Index: 822270 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2149. Min Act: -0.0001

Data Index: 746237 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1996. Min Act: -0.0001

Data Index: 184616 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1954. Min Act: -0.0001

Data Index: 507713 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1975. Min Act: -0.0001

Data Index: 829569 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2243. Min Act: -0.0001

Data Index: 232408 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2049. Min Act: -0.0001

Data Index: 1271146 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2108. Min Act: -0.0001

Data Index: 60207 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1935. Min Act: -0.0001

Data Index: 773032 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2086. Min Act: -0.0001

Data Index: 579373 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1924. Min Act: -0.0001

Data Index: 52188 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2001. Min Act: -0.0001

Data Index: 671632 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2059. Min Act: -0.0001

Data Index: 343964 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.2120. Min Act: -0.0001

Data Index: 1249502 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.2449. Min Range: -0.2449

Max Act: 0.1753. Min Act: -0.0001

Data Index: 700456 (C4 (Web Text))

Max Activating Token Index: 636