Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 908 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0836. Min Act: -0.0003

Data Index: 995864 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0807. Min Act: -0.0004

Data Index: 1342559 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0792. Min Act: -0.0004

Data Index: 1263182 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0755. Min Act: -0.0003

Data Index: 976558 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0758. Min Act: -0.0004

Data Index: 872881 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0747. Min Act: -0.0003

Data Index: 51273 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0693. Min Act: -0.0003

Data Index: 777028 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0712. Min Act: -0.0003

Data Index: 135064 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0697. Min Act: -0.0003

Data Index: 1335071 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0690. Min Act: -0.0003

Data Index: 1054861 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0707. Min Act: -0.0003

Data Index: 1094196 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0666. Min Act: -0.0004

Data Index: 715400 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0672. Min Act: -0.0003

Data Index: 550379 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0680. Min Act: -0.0003

Data Index: 924637 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0669. Min Act: -0.0003

Data Index: 1319050 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0673. Min Act: -0.0003

Data Index: 1078202 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0662. Min Act: -0.0004

Data Index: 511384 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0655. Min Act: -0.0003

Data Index: 1296486 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0670. Min Act: -0.0003

Data Index: 456383 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0665. Min Act: -0.0003

Data Index: 383400 (C4 (Web Text))

Max Activating Token Index: 98