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

Dataset: The Pile

Neuron 1614 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.7347. Min Act: -0.0000

Data Index: 569230 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1275020 (The Pile)

Max Activating Token Index: 569

Text #2

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.7731. Min Act: -0.0000

Data Index: 184634 (The Pile)

Max Activating Token Index: 318

Text #3

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6899. Min Act: -0.0000

Data Index: 129470 (The Pile)

Max Activating Token Index: 1012

Text #4

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.7151. Min Act: -0.0000

Data Index: 1454843 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.7392. Min Act: -0.0000

Data Index: 698498 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6610. Min Act: -0.0000

Data Index: 978740 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1531005 (The Pile)

Max Activating Token Index: 615

Text #8

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6931. Min Act: -0.0000

Data Index: 1241368 (The Pile)

Max Activating Token Index: 582

Text #9

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6147. Min Act: -0.0000

Data Index: 1303492 (The Pile)

Max Activating Token Index: 677

Text #10

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6643. Min Act: -0.0000

Data Index: 1567566 (The Pile)

Max Activating Token Index: 79

Text #11

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1270420 (The Pile)

Max Activating Token Index: 901

Text #12

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6370. Min Act: -0.0000

Data Index: 332737 (The Pile)

Max Activating Token Index: 53

Text #13

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1184777 (The Pile)

Max Activating Token Index: 627

Text #14

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.5642. Min Act: -0.0000

Data Index: 982427 (The Pile)

Max Activating Token Index: 651

Text #15

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6393. Min Act: -0.0000

Data Index: 1387709 (The Pile)

Max Activating Token Index: 254

Text #16

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1747205 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1284921 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1515714 (The Pile)

Max Activating Token Index: 562

Text #19

Max Range: 0.7731. Min Range: -0.7731

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1887222 (The Pile)

Max Activating Token Index: 1003