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

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

Neuron 200 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: 0.0701. Min Range: -0.0701

Max Act: 0.0701. Min Act: -0.0005

Data Index: 133536 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0641. Min Act: -0.0005

Data Index: 215861 (C4 (Web Text))

Max Activating Token Index: 847

Text #2

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0622. Min Act: -0.0005

Data Index: 477084 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0594. Min Act: -0.0005

Data Index: 42456 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0596. Min Act: -0.0005

Data Index: 817572 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0596. Min Act: -0.0005

Data Index: 1047194 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0550. Min Act: -0.0005

Data Index: 689038 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0586. Min Act: -0.0005

Data Index: 651755 (C4 (Web Text))

Max Activating Token Index: 905

Text #8

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0580. Min Act: -0.0005

Data Index: 1222185 (C4 (Web Text))

Max Activating Token Index: 572

Text #9

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0574. Min Act: -0.0005

Data Index: 181760 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0561. Min Act: -0.0005

Data Index: 1140230 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0571. Min Act: -0.0005

Data Index: 45141 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0591. Min Act: -0.0005

Data Index: 1056383 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0567. Min Act: -0.0005

Data Index: 1050759 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0577. Min Act: -0.0005

Data Index: 947954 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0567. Min Act: -0.0005

Data Index: 44899 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0533. Min Act: -0.0005

Data Index: 119116 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0510. Min Act: -0.0005

Data Index: 422164 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0531. Min Act: -0.0005

Data Index: 567360 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0538. Min Act: -0.0005

Data Index: 424163 (C4 (Web Text))

Max Activating Token Index: 252