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

Dataset: The Pile

Neuron 2849 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: 1.0117. Min Range: -1.0117

Max Act: 1.0117. Min Act: -0.0000

Data Index: 1229423 (The Pile)

Max Activating Token Index: 497

Text #1

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1946041 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.8387. Min Act: -0.0000

Data Index: 1283950 (The Pile)

Max Activating Token Index: 767

Text #3

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.8052. Min Act: -0.0000

Data Index: 296406 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.8198. Min Act: -0.0000

Data Index: 640898 (The Pile)

Max Activating Token Index: 939

Text #5

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1730699 (The Pile)

Max Activating Token Index: 139

Text #6

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7314. Min Act: -0.0000

Data Index: 353965 (The Pile)

Max Activating Token Index: 564

Text #7

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7505. Min Act: -0.0000

Data Index: 499734 (The Pile)

Max Activating Token Index: 91

Text #8

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.6789. Min Act: -0.0000

Data Index: 324431 (The Pile)

Max Activating Token Index: 819

Text #9

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1169432 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1469999 (The Pile)

Max Activating Token Index: 839

Text #11

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1527307 (The Pile)

Max Activating Token Index: 957

Text #12

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1408347 (The Pile)

Max Activating Token Index: 917

Text #13

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.6787. Min Act: -0.0000

Data Index: 109692 (The Pile)

Max Activating Token Index: 922

Text #14

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1944195 (The Pile)

Max Activating Token Index: 957

Text #15

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1522993 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7277. Min Act: -0.0000

Data Index: 599358 (The Pile)

Max Activating Token Index: 49

Text #17

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.6691. Min Act: -0.0000

Data Index: 1785409 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.6954. Min Act: -0.0000

Data Index: 64058 (The Pile)

Max Activating Token Index: 644

Text #19

Max Range: 1.0117. Min Range: -1.0117

Max Act: 0.7207. Min Act: -0.0000

Data Index: 944201 (The Pile)

Max Activating Token Index: 61