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

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

Neuron 2670 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.4424. Min Act: -0.0000

Data Index: 347765 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.2563. Min Act: -0.0000

Data Index: 808533 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.1324. Min Act: -0.0000

Data Index: 461255 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.0688. Min Act: -0.0000

Data Index: 138878 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.1024. Min Act: -0.0000

Data Index: 720465 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.0697. Min Act: -0.0000

Data Index: 460612 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.0950. Min Act: -0.0000

Data Index: 317865 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.0648. Min Act: -0.0000

Data Index: 959567 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1329065 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.8872. Min Act: -0.0000

Data Index: 1315221 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9787. Min Act: -0.0000

Data Index: 1172318 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9285. Min Act: -0.0000

Data Index: 1036729 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1031557 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.0014. Min Act: -0.0000

Data Index: 256116 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9750. Min Act: -0.0000

Data Index: 468743 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9643. Min Act: -0.0000

Data Index: 648942 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 1.4424. Min Range: -1.4424

Max Act: 1.0043. Min Act: -0.0000

Data Index: 1219814 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9306. Min Act: -0.0000

Data Index: 325198 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9570. Min Act: -0.0000

Data Index: 695254 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 1.4424. Min Range: -1.4424

Max Act: 0.9812. Min Act: -0.0000

Data Index: 361090 (C4 (Web Text))

Max Activating Token Index: 410