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

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

Neuron 2226 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: 0.5876. Min Range: -0.5876

Max Act: 0.5263. Min Act: -0.0002

Data Index: 808116 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.5876. Min Act: -0.0002

Data Index: 590535 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4850. Min Act: -0.0002

Data Index: 431135 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.5070. Min Act: -0.0002

Data Index: 745553 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.5067. Min Act: -0.0002

Data Index: 911544 (C4 (Web Text))

Max Activating Token Index: 461

Text #5

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.5112. Min Act: -0.0002

Data Index: 284810 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.5106. Min Act: -0.0002

Data Index: 1337541 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4674. Min Act: -0.0002

Data Index: 379764 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4693. Min Act: -0.0002

Data Index: 1076058 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4852. Min Act: -0.0002

Data Index: 789273 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4666. Min Act: -0.0002

Data Index: 140107 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4398. Min Act: -0.0002

Data Index: 1266097 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4386. Min Act: -0.0002

Data Index: 125256 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.5388. Min Act: -0.0002

Data Index: 721902 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4628. Min Act: -0.0002

Data Index: 735297 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4496. Min Act: -0.0002

Data Index: 704161 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4790. Min Act: -0.0002

Data Index: 1096599 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4464. Min Act: -0.0002

Data Index: 572183 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4465. Min Act: -0.0002

Data Index: 137071 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.5876. Min Range: -0.5876

Max Act: 0.4682. Min Act: -0.0002

Data Index: 763691 (C4 (Web Text))

Max Activating Token Index: 373