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

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

Neuron 2008 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9743. Min Act: -0.0002

Data Index: 256536 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9602. Min Act: -0.0001

Data Index: 202657 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9862. Min Act: -0.0002

Data Index: 869158 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9612. Min Act: -0.0002

Data Index: 488319 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9740. Min Act: -0.0002

Data Index: 593141 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8748. Min Act: -0.0001

Data Index: 966007 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9824. Min Act: -0.0002

Data Index: 797197 (C4 (Web Text))

Max Activating Token Index: 206

Text #7

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9921. Min Act: -0.0002

Data Index: 529364 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8848. Min Act: -0.0001

Data Index: 1348338 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9643. Min Act: -0.0002

Data Index: 1022546 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8508. Min Act: -0.0002

Data Index: 1137073 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8825. Min Act: -0.0002

Data Index: 424520 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9017. Min Act: -0.0002

Data Index: 990064 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8888. Min Act: -0.0001

Data Index: 837470 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9075. Min Act: -0.0001

Data Index: 1175627 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9355. Min Act: -0.0001

Data Index: 750340 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9093. Min Act: -0.0002

Data Index: 807142 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9813. Min Act: -0.0002

Data Index: 324100 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.8569. Min Act: -0.0002

Data Index: 1076393 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.9921. Min Range: -0.9921

Max Act: 0.9136. Min Act: -0.0001

Data Index: 686218 (C4 (Web Text))

Max Activating Token Index: 383