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

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

Neuron 2427 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.9464. Min Act: -0.0002

Data Index: 874601 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.8849. Min Act: -0.0002

Data Index: 1123351 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.5096. Min Act: -0.0002

Data Index: 593433 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.5632. Min Act: -0.0002

Data Index: 166387 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.5419. Min Act: -0.0002

Data Index: 603917 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.5104. Min Act: -0.0003

Data Index: 769762 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.4847. Min Act: -0.0002

Data Index: 1284229 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.4622. Min Act: -0.0002

Data Index: 172366 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.4323. Min Act: -0.0002

Data Index: 349387 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.3578. Min Act: -0.0002

Data Index: 669869 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.3816. Min Act: -0.0002

Data Index: 1347250 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.2937. Min Act: -0.0002

Data Index: 636011 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.4145. Min Act: -0.0002

Data Index: 873850 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.2996. Min Act: -0.0002

Data Index: 532169 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.4105. Min Act: -0.0002

Data Index: 709380 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.3859. Min Act: -0.0002

Data Index: 254730 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.3501. Min Act: -0.0002

Data Index: 1229491 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.3089. Min Act: -0.0002

Data Index: 152077 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.3034. Min Act: -0.0002

Data Index: 276338 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.9464. Min Range: -1.9464

Max Act: 1.4113. Min Act: -0.0002

Data Index: 344702 (C4 (Web Text))

Max Activating Token Index: 75