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

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

Neuron 1828 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: 0.0710. Min Range: -0.0710

Max Act: 0.0710. Min Act: -0.0003

Data Index: 666898 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0638. Min Act: -0.0003

Data Index: 846343 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1327008 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0604. Min Act: -0.0003

Data Index: 109715 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0605. Min Act: -0.0002

Data Index: 256627 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0595. Min Act: -0.0003

Data Index: 893315 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1141644 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0594. Min Act: -0.0003

Data Index: 643472 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0572. Min Act: -0.0004

Data Index: 1037420 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0566. Min Act: -0.0003

Data Index: 252644 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1008598 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0568. Min Act: -0.0003

Data Index: 162864 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0568. Min Act: -0.0003

Data Index: 943994 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0570. Min Act: -0.0003

Data Index: 473887 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0568. Min Act: -0.0004

Data Index: 751170 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0576. Min Act: -0.0003

Data Index: 208253 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0545. Min Act: -0.0003

Data Index: 238359 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0560. Min Act: -0.0003

Data Index: 721718 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0562. Min Act: -0.0003

Data Index: 574353 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.0710. Min Range: -0.0710

Max Act: 0.0543. Min Act: -0.0003

Data Index: 711170 (C4 (Web Text))

Max Activating Token Index: 382