Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 583 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2887. Min Range: -2.2887

Max Act: 2.2887. Min Act: -0.0000

Data Index: 950000 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 2.2887. Min Range: -2.2887

Max Act: 2.0673. Min Act: -0.0000

Data Index: 1519474 (Python Code)

Max Activating Token Index: 693

Text #2

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.9361. Min Act: -0.0000

Data Index: 617088 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.8951. Min Act: -0.0000

Data Index: 1446115 (Python Code)

Max Activating Token Index: 537

Text #4

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.8668. Min Act: -0.0000

Data Index: 1147962 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.8583. Min Act: -0.0000

Data Index: 571235 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.7878. Min Act: -0.0000

Data Index: 157983 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.7634. Min Act: -0.0000

Data Index: 1393442 (Python Code)

Max Activating Token Index: 643

Text #8

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.6556. Min Act: -0.0000

Data Index: 255489 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.7573. Min Act: 0.0000

Data Index: 991177 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.6961. Min Act: 0.0000

Data Index: 846458 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.5931. Min Act: -0.0000

Data Index: 712639 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.6845. Min Act: -0.0000

Data Index: 1629215 (Python Code)

Max Activating Token Index: 59

Text #13

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.7678. Min Act: -0.0000

Data Index: 247325 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.3668. Min Act: -0.0000

Data Index: 1278101 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.6562. Min Act: -0.0000

Data Index: 156802 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.7502. Min Act: -0.0000

Data Index: 1003354 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.6349. Min Act: -0.0000

Data Index: 704489 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.5243. Min Act: -0.0000

Data Index: 773898 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 2.2887. Min Range: -2.2887

Max Act: 1.5035. Min Act: -0.0000

Data Index: 1044248 (C4 (Web Text))

Max Activating Token Index: 959