Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4822 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0463. Min Act: -0.0001

Data Index: 1061511 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.1561. Min Act: -0.0001

Data Index: 1022506 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.1047. Min Act: -0.0001

Data Index: 928400 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.1723. Min Act: -0.0001

Data Index: 911885 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0731. Min Act: -0.0001

Data Index: 686622 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.1408. Min Act: -0.0001

Data Index: 202543 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.5985. Min Act: -0.0001

Data Index: 843716 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0718. Min Act: -0.0001

Data Index: 346632 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.9016. Min Act: -0.0001

Data Index: 1151924 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0535. Min Act: -0.0001

Data Index: 657489 (C4 (Web Text))

Max Activating Token Index: 565

Text #10

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.2660. Min Act: -0.0001

Data Index: 1023368 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0520. Min Act: -0.0001

Data Index: 161755 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.9178. Min Act: -0.0001

Data Index: 1010690 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0008. Min Act: -0.0001

Data Index: 921479 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.9855. Min Act: -0.0001

Data Index: 661910 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.9940. Min Act: -0.0001

Data Index: 964281 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 1.2660. Min Range: -1.2660

Max Act: 1.0105. Min Act: -0.0001

Data Index: 975542 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.8319. Min Act: -0.0001

Data Index: 228369 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.9140. Min Act: -0.0001

Data Index: 141453 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 1.2660. Min Range: -1.2660

Max Act: 0.8354. Min Act: -0.0001

Data Index: 736566 (C4 (Web Text))

Max Activating Token Index: 104