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

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

Neuron 1516 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0715. Min Range: -4.0715

Max Act: 4.0715. Min Act: -0.0000

Data Index: 322143 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.8707. Min Act: -0.0000

Data Index: 203897 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.7436. Min Act: -0.0000

Data Index: 636775 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.8731. Min Act: -0.0000

Data Index: 896206 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.6532. Min Act: -0.0000

Data Index: 126507 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.6540. Min Act: -0.0000

Data Index: 691075 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.6246. Min Act: -0.0000

Data Index: 718887 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.5761. Min Act: -0.0000

Data Index: 742974 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.5874. Min Act: -0.0000

Data Index: 353499 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.4305. Min Act: -0.0000

Data Index: 949917 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.4139. Min Act: -0.0000

Data Index: 824260 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.7047. Min Act: -0.0000

Data Index: 285090 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.4217. Min Act: -0.0000

Data Index: 260836 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.4849. Min Act: -0.0000

Data Index: 725578 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.4004. Min Act: -0.0000

Data Index: 660656 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.3631. Min Act: -0.0000

Data Index: 802282 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.0950. Min Act: -0.0000

Data Index: 1236674 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.0484. Min Act: -0.0000

Data Index: 810530 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.2075. Min Act: -0.0000

Data Index: 246768 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 4.0715. Min Range: -4.0715

Max Act: 3.2064. Min Act: -0.0000

Data Index: 916947 (C4 (Web Text))

Max Activating Token Index: 765