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

Dataset: The Pile

Neuron 2153 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0677. Min Range: -3.0677

Max Act: 3.0677. Min Act: -0.0000

Data Index: 728454 (The Pile)

Max Activating Token Index: 112

Text #1

Max Range: 3.0677. Min Range: -3.0677

Max Act: 2.9430. Min Act: -0.0000

Data Index: 1573930 (The Pile)

Max Activating Token Index: 607

Text #2

Max Range: 3.0677. Min Range: -3.0677

Max Act: 3.0335. Min Act: -0.0000

Data Index: 743387 (The Pile)

Max Activating Token Index: 505

Text #3

Max Range: 3.0677. Min Range: -3.0677

Max Act: 2.8851. Min Act: -0.0000

Data Index: 225850 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 3.0677. Min Range: -3.0677

Max Act: 2.5452. Min Act: -0.0000

Data Index: 1624879 (The Pile)

Max Activating Token Index: 272

Text #5

Max Range: 3.0677. Min Range: -3.0677

Max Act: 2.7614. Min Act: -0.0000

Data Index: 648307 (The Pile)

Max Activating Token Index: 671

Text #6

Max Range: 3.0677. Min Range: -3.0677

Max Act: 2.7112. Min Act: -0.0000

Data Index: 1354933 (The Pile)

Max Activating Token Index: 778

Text #7

Max Range: 3.0677. Min Range: -3.0677

Max Act: 2.4426. Min Act: -0.0000

Data Index: 874881 (The Pile)

Max Activating Token Index: 730

Text #8

Max Range: 3.0677. Min Range: -3.0677

Max Act: 2.4151. Min Act: -0.0000

Data Index: 1086364 (The Pile)

Max Activating Token Index: 472

Text #9

Max Range: 3.0677. Min Range: -3.0677

Max Act: 2.4863. Min Act: -0.0000

Data Index: 1332754 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 3.0677. Min Range: -3.0677

Max Act: 2.2936. Min Act: -0.0000

Data Index: 1278285 (The Pile)

Max Activating Token Index: 419

Text #11

Max Range: 3.0677. Min Range: -3.0677

Max Act: 2.3950. Min Act: -0.0000

Data Index: 108821 (The Pile)

Max Activating Token Index: 571

Text #12

Max Range: 3.0677. Min Range: -3.0677

Max Act: 2.1361. Min Act: -0.0000

Data Index: 853032 (The Pile)

Max Activating Token Index: 449

Text #13

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.8097. Min Act: -0.0000

Data Index: 1291080 (The Pile)

Max Activating Token Index: 979

Text #14

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.6203. Min Act: -0.0000

Data Index: 1529196 (The Pile)

Max Activating Token Index: 957

Text #15

Max Range: 3.0677. Min Range: -3.0677

Max Act: 2.1637. Min Act: -0.0000

Data Index: 1111422 (The Pile)

Max Activating Token Index: 604

Text #16

Max Range: 3.0677. Min Range: -3.0677

Max Act: 2.1261. Min Act: -0.0000

Data Index: 1466130 (The Pile)

Max Activating Token Index: 477

Text #17

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.9629. Min Act: -0.0000

Data Index: 1672947 (The Pile)

Max Activating Token Index: 614

Text #18

Max Range: 3.0677. Min Range: -3.0677

Max Act: 2.1263. Min Act: -0.0000

Data Index: 751852 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 3.0677. Min Range: -3.0677

Max Act: 1.9874. Min Act: -0.0000

Data Index: 591524 (The Pile)

Max Activating Token Index: 549