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

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

Neuron 2470 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0985. Min Act: -0.0001

Data Index: 78682 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0898. Min Act: -0.0001

Data Index: 937559 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0902. Min Act: -0.0001

Data Index: 219441 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0882. Min Act: -0.0001

Data Index: 174373 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1306786 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0836. Min Act: -0.0001

Data Index: 238659 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0857. Min Act: -0.0001

Data Index: 965503 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0820. Min Act: -0.0001

Data Index: 212439 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0886. Min Act: -0.0001

Data Index: 349647 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0789. Min Act: -0.0001

Data Index: 467813 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0844. Min Act: -0.0001

Data Index: 547137 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0835. Min Act: -0.0001

Data Index: 577667 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0854. Min Act: -0.0001

Data Index: 676006 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0774. Min Act: -0.0001

Data Index: 70732 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1307818 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0854. Min Act: -0.0001

Data Index: 494571 (C4 (Web Text))

Max Activating Token Index: 262

Text #16

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0778. Min Act: -0.0001

Data Index: 423388 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0805. Min Act: -0.0001

Data Index: 906443 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0820. Min Act: -0.0001

Data Index: 93525 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0727. Min Act: -0.0001

Data Index: 500371 (C4 (Web Text))

Max Activating Token Index: 700