Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2801 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4865. Min Act: -0.0003

Data Index: 40187 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4462. Min Act: -0.0003

Data Index: 159176 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4573. Min Act: -0.0003

Data Index: 1332322 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4316. Min Act: -0.0003

Data Index: 731341 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4112. Min Act: -0.0003

Data Index: 209113 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4213. Min Act: -0.0003

Data Index: 839629 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4665. Min Act: -0.0003

Data Index: 344014 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4201. Min Act: -0.0003

Data Index: 364895 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4380. Min Act: -0.0003

Data Index: 224523 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4278. Min Act: -0.0003

Data Index: 520085 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4090. Min Act: -0.0003

Data Index: 309429 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4077. Min Act: -0.0003

Data Index: 1324469 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4227. Min Act: -0.0003

Data Index: 955345 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3871. Min Act: -0.0003

Data Index: 333178 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3878. Min Act: -0.0003

Data Index: 244793 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4499. Min Act: -0.0003

Data Index: 450198 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3745. Min Act: -0.0003

Data Index: 534946 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.4017. Min Act: -0.0003

Data Index: 507408 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3792. Min Act: -0.0003

Data Index: 677270 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.4865. Min Range: -0.4865

Max Act: 0.3917. Min Act: -0.0003

Data Index: 827632 (C4 (Web Text))

Max Activating Token Index: 828