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

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

Neuron 580 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: 0.6678. Min Range: -0.6678

Max Act: 0.6678. Min Act: -0.0003

Data Index: 1159265 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5007. Min Act: -0.0003

Data Index: 1018397 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5522. Min Act: -0.0003

Data Index: 411643 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4830. Min Act: -0.0003

Data Index: 402575 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5235. Min Act: -0.0003

Data Index: 118605 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5590. Min Act: -0.0003

Data Index: 68793 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.5047. Min Act: -0.0003

Data Index: 625603 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4938. Min Act: -0.0003

Data Index: 1299927 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4651. Min Act: -0.0003

Data Index: 1138388 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4641. Min Act: -0.0003

Data Index: 547710 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4948. Min Act: -0.0003

Data Index: 1031681 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4215. Min Act: -0.0003

Data Index: 1210815 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.3877. Min Act: -0.0003

Data Index: 939114 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4386. Min Act: -0.0003

Data Index: 656890 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4245. Min Act: -0.0003

Data Index: 617753 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4369. Min Act: -0.0003

Data Index: 1195255 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4206. Min Act: -0.0003

Data Index: 966869 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.4014. Min Act: -0.0003

Data Index: 255281 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.3767. Min Act: -0.0003

Data Index: 162221 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.6678. Min Range: -0.6678

Max Act: 0.3875. Min Act: -0.0003

Data Index: 881470 (C4 (Web Text))

Max Activating Token Index: 338