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

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

Neuron 4340 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1236053 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1055535 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5987. Min Act: -0.0000

Data Index: 700483 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5371. Min Act: -0.0000

Data Index: 186407 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.6050. Min Act: -0.0000

Data Index: 453482 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5418. Min Act: -0.0000

Data Index: 678770 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.6243. Min Act: -0.0000

Data Index: 75973 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5156. Min Act: -0.0000

Data Index: 552453 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5568. Min Act: -0.0000

Data Index: 646798 (C4 (Web Text))

Max Activating Token Index: 111

Text #9

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4963. Min Act: -0.0000

Data Index: 664873 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5699. Min Act: -0.0000

Data Index: 856473 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4725. Min Act: -0.0000

Data Index: 234122 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1015424 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4600. Min Act: -0.0000

Data Index: 253960 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4899. Min Act: -0.0000

Data Index: 481762 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4145. Min Act: -0.0000

Data Index: 965283 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1154898 (C4 (Web Text))

Max Activating Token Index: 79

Text #17

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.4808. Min Act: -0.0000

Data Index: 433123 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5100. Min Act: -0.0000

Data Index: 905366 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 0.6338. Min Range: -0.6338

Max Act: 0.5086. Min Act: -0.0000

Data Index: 499893 (C4 (Web Text))

Max Activating Token Index: 893