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

Dataset: The Pile

Neuron 1449 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.2162. Min Act: -0.0000

Data Index: 739699 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1376862 (The Pile)

Max Activating Token Index: 887

Text #2

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.2030. Min Act: -0.0000

Data Index: 1720415 (The Pile)

Max Activating Token Index: 761

Text #3

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1002821 (The Pile)

Max Activating Token Index: 37

Text #4

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1789. Min Act: -0.0000

Data Index: 366466 (The Pile)

Max Activating Token Index: 105

Text #5

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1786. Min Act: -0.0000

Data Index: 957297 (The Pile)

Max Activating Token Index: 278

Text #6

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1882. Min Act: -0.0000

Data Index: 299781 (The Pile)

Max Activating Token Index: 633

Text #7

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1746. Min Act: -0.0000

Data Index: 515069 (The Pile)

Max Activating Token Index: 416

Text #8

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1247985 (The Pile)

Max Activating Token Index: 371

Text #9

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1410. Min Act: -0.0000

Data Index: 1351741 (The Pile)

Max Activating Token Index: 696

Text #10

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1675027 (The Pile)

Max Activating Token Index: 450

Text #11

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1587. Min Act: -0.0000

Data Index: 1072627 (The Pile)

Max Activating Token Index: 676

Text #12

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1583. Min Act: -0.0000

Data Index: 792933 (The Pile)

Max Activating Token Index: 25

Text #13

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1476. Min Act: -0.0000

Data Index: 852851 (The Pile)

Max Activating Token Index: 986

Text #14

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1551. Min Act: -0.0000

Data Index: 1832264 (The Pile)

Max Activating Token Index: 354

Text #15

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1821945 (The Pile)

Max Activating Token Index: 855

Text #16

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1431. Min Act: -0.0000

Data Index: 1370641 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1610. Min Act: -0.0000

Data Index: 801360 (The Pile)

Max Activating Token Index: 541

Text #18

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1408. Min Act: -0.0000

Data Index: 929646 (The Pile)

Max Activating Token Index: 608

Text #19

Max Range: 0.2162. Min Range: -0.2162

Max Act: 0.1460. Min Act: -0.0000

Data Index: 1545790 (The Pile)

Max Activating Token Index: 939