Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1679 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0721. Min Act: -0.0005

Data Index: 847718 (C4 (Web Text))

Max Activating Token Index: 299

Text #1

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0730. Min Act: -0.0005

Data Index: 674056 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0650. Min Act: -0.0005

Data Index: 675078 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0632. Min Act: -0.0005

Data Index: 1328874 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0592. Min Act: -0.0005

Data Index: 640280 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0594. Min Act: -0.0005

Data Index: 252349 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0552. Min Act: -0.0005

Data Index: 1019193 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0543. Min Act: -0.0005

Data Index: 4949 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0527. Min Act: -0.0005

Data Index: 1055239 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0529. Min Act: -0.0005

Data Index: 1189899 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0539. Min Act: -0.0005

Data Index: 949991 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0566. Min Act: -0.0005

Data Index: 666753 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0553. Min Act: -0.0005

Data Index: 658404 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0554. Min Act: -0.0005

Data Index: 25918 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0541. Min Act: -0.0005

Data Index: 298062 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0581. Min Act: -0.0005

Data Index: 1290523 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0548. Min Act: -0.0005

Data Index: 1213265 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0543. Min Act: -0.0005

Data Index: 287162 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0540. Min Act: -0.0005

Data Index: 593569 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0523. Min Act: -0.0005

Data Index: 109865 (C4 (Web Text))

Max Activating Token Index: 894