Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2715 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.1369. Min Act: -0.0001

Data Index: 639459 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.1715. Min Act: -0.0000

Data Index: 780315 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.1768. Min Act: -0.0001

Data Index: 707401 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.0942. Min Act: -0.0001

Data Index: 190494 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.0911. Min Act: -0.0001

Data Index: 148448 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.0647. Min Act: -0.0000

Data Index: 198221 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.0749. Min Act: -0.0001

Data Index: 1043680 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1028385 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.0777. Min Act: -0.0001

Data Index: 287491 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.0238. Min Act: -0.0000

Data Index: 4386 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9860. Min Act: -0.0001

Data Index: 34236 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.0442. Min Act: -0.0000

Data Index: 284748 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9721. Min Act: -0.0001

Data Index: 991184 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.0076. Min Act: -0.0001

Data Index: 125065 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.0308. Min Act: -0.0001

Data Index: 820713 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 1.1768. Min Range: -1.1768

Max Act: 1.0288. Min Act: -0.0001

Data Index: 602271 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9944. Min Act: -0.0000

Data Index: 386996 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9285. Min Act: -0.0001

Data Index: 1320951 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9798. Min Act: -0.0001

Data Index: 847676 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 1.1768. Min Range: -1.1768

Max Act: 0.9572. Min Act: -0.0000

Data Index: 897268 (C4 (Web Text))

Max Activating Token Index: 557