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

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

Neuron 4706 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.8488. Min Act: -0.0000

Data Index: 498594 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7808. Min Act: -0.0000

Data Index: 530824 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7579. Min Act: -0.0000

Data Index: 63255 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.8008. Min Act: -0.0000

Data Index: 649500 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7552. Min Act: -0.0000

Data Index: 429125 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7344. Min Act: -0.0000

Data Index: 410777 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7153. Min Act: -0.0000

Data Index: 937186 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7332. Min Act: -0.0000

Data Index: 628013 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7812. Min Act: -0.0000

Data Index: 961114 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6959. Min Act: -0.0000

Data Index: 1284907 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7072. Min Act: -0.0000

Data Index: 481024 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6692. Min Act: -0.0000

Data Index: 390489 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6637. Min Act: -0.0000

Data Index: 865619 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6868. Min Act: -0.0000

Data Index: 470455 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6787. Min Act: -0.0000

Data Index: 804950 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6545. Min Act: -0.0000

Data Index: 902856 (C4 (Web Text))

Max Activating Token Index: 427

Text #16

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6723. Min Act: -0.0000

Data Index: 232823 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6655. Min Act: -0.0000

Data Index: 189625 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1295018 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.8488. Min Range: -0.8488

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1185441 (C4 (Web Text))

Max Activating Token Index: 230