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

Dataset: The Pile

Neuron 2480 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1662769 (The Pile)

Max Activating Token Index: 11

Text #1

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1392643 (The Pile)

Max Activating Token Index: 696

Text #2

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.7310. Min Act: -0.0000

Data Index: 785192 (The Pile)

Max Activating Token Index: 579

Text #3

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6960. Min Act: -0.0000

Data Index: 549271 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1160825 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.7205. Min Act: -0.0000

Data Index: 1908812 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6271. Min Act: -0.0000

Data Index: 374071 (The Pile)

Max Activating Token Index: 168

Text #7

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6013. Min Act: -0.0000

Data Index: 157919 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6126. Min Act: -0.0000

Data Index: 282004 (The Pile)

Max Activating Token Index: 549

Text #9

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5907. Min Act: -0.0000

Data Index: 412449 (The Pile)

Max Activating Token Index: 565

Text #10

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6299. Min Act: -0.0000

Data Index: 154488 (The Pile)

Max Activating Token Index: 444

Text #11

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1635326 (The Pile)

Max Activating Token Index: 930

Text #12

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5840. Min Act: -0.0000

Data Index: 582561 (The Pile)

Max Activating Token Index: 6

Text #13

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5485. Min Act: -0.0000

Data Index: 727417 (The Pile)

Max Activating Token Index: 720

Text #14

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5760. Min Act: -0.0000

Data Index: 427716 (The Pile)

Max Activating Token Index: 481

Text #15

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1194372 (The Pile)

Max Activating Token Index: 912

Text #16

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1773098 (The Pile)

Max Activating Token Index: 610

Text #17

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5610. Min Act: -0.0000

Data Index: 68768 (The Pile)

Max Activating Token Index: 729

Text #18

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.6003. Min Act: -0.0000

Data Index: 488956 (The Pile)

Max Activating Token Index: 555

Text #19

Max Range: 0.8723. Min Range: -0.8723

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1845979 (The Pile)

Max Activating Token Index: 652