Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2557 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1673. Min Range: -1.1673

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1247245 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 1.1673. Min Range: -1.1673

Max Act: 1.1362. Min Act: -0.0000

Data Index: 982711 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 1.1673. Min Range: -1.1673

Max Act: 1.0756. Min Act: -0.0001

Data Index: 1492666 (Python Code)

Max Activating Token Index: 863

Text #3

Max Range: 1.1673. Min Range: -1.1673

Max Act: 1.1673. Min Act: 0.0001

Data Index: 1287516 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 1.1673. Min Range: -1.1673

Max Act: 1.0587. Min Act: -0.0000

Data Index: 1340778 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 1.1673. Min Range: -1.1673

Max Act: 1.0775. Min Act: -0.0001

Data Index: 1439242 (Python Code)

Max Activating Token Index: 631

Text #6

Max Range: 1.1673. Min Range: -1.1673

Max Act: 1.0037. Min Act: -0.0001

Data Index: 1267977 (C4 (Web Text))

Max Activating Token Index: 317

Text #7

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9911. Min Act: -0.0001

Data Index: 631353 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9766. Min Act: -0.0001

Data Index: 1585227 (Python Code)

Max Activating Token Index: 815

Text #9

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9130. Min Act: -0.0000

Data Index: 932746 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9363. Min Act: 0.0000

Data Index: 530186 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.7703. Min Act: -0.0001

Data Index: 262959 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.8655. Min Act: 0.0000

Data Index: 1262227 (C4 (Web Text))

Max Activating Token Index: 333

Text #13

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.9121. Min Act: -0.0000

Data Index: 656619 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.8503. Min Act: -0.0000

Data Index: 671195 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.8211. Min Act: -0.0000

Data Index: 294059 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.8706. Min Act: -0.0001

Data Index: 1394112 (Python Code)

Max Activating Token Index: 995

Text #17

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.8204. Min Act: 0.0000

Data Index: 1273958 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.6273. Min Act: -0.0001

Data Index: 788092 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 1.1673. Min Range: -1.1673

Max Act: 0.8792. Min Act: -0.0001

Data Index: 1451381 (Python Code)

Max Activating Token Index: 723