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

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

Neuron 5872 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.7420. Min Act: -0.0000

Data Index: 1357530 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.8069. Min Act: 0.0000

Data Index: 529027 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.4168. Min Act: -0.0000

Data Index: 425363 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.4969. Min Act: -0.0000

Data Index: 1002626 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.5270. Min Act: -0.0000

Data Index: 1503515 (Python Code)

Max Activating Token Index: 246

Text #5

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.4372. Min Act: -0.0000

Data Index: 963903 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.4159. Min Act: -0.0000

Data Index: 527760 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.3823. Min Act: -0.0000

Data Index: 435985 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.4167. Min Act: -0.0000

Data Index: 626 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.3087. Min Act: -0.0000

Data Index: 593957 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.2816. Min Act: 0.0000

Data Index: 1298486 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.2588. Min Act: -0.0000

Data Index: 692044 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.2355. Min Act: 0.0000

Data Index: 961228 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.1862. Min Act: -0.0000

Data Index: 1232423 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.1161. Min Act: 0.0000

Data Index: 329311 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.1699. Min Act: -0.0000

Data Index: 1050411 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.1736. Min Act: -0.0000

Data Index: 1186029 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.1664. Min Act: -0.0000

Data Index: 1177470 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.1689. Min Act: -0.0000

Data Index: 495832 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 1.8069. Min Range: -1.8069

Max Act: 1.2352. Min Act: -0.0000

Data Index: 221043 (C4 (Web Text))

Max Activating Token Index: 275