Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1498 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.4468. Min Act: -0.0002

Data Index: 522859 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3561. Min Act: -0.0002

Data Index: 142557 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3565. Min Act: -0.0001

Data Index: 884406 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3410. Min Act: -0.0002

Data Index: 1062915 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3356. Min Act: -0.0001

Data Index: 374921 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3265. Min Act: -0.0002

Data Index: 1069415 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3341. Min Act: -0.0002

Data Index: 1223308 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3122. Min Act: -0.0002

Data Index: 702616 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3170. Min Act: -0.0002

Data Index: 1043857 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3154. Min Act: -0.0002

Data Index: 102299 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3113. Min Act: -0.0002

Data Index: 593781 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3060. Min Act: -0.0002

Data Index: 904598 (C4 (Web Text))

Max Activating Token Index: 549

Text #12

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3179. Min Act: -0.0002

Data Index: 521856 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3192. Min Act: -0.0002

Data Index: 184865 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3074. Min Act: -0.0001

Data Index: 1034632 (C4 (Web Text))

Max Activating Token Index: 64

Text #15

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3228. Min Act: -0.0001

Data Index: 984362 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.2954. Min Act: -0.0002

Data Index: 924964 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.2918. Min Act: -0.0002

Data Index: 34231 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3391. Min Act: -0.0002

Data Index: 390966 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.4468. Min Range: -0.4468

Max Act: 0.3085. Min Act: -0.0002

Data Index: 24533 (C4 (Web Text))

Max Activating Token Index: 382