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

Dataset: The Pile

Neuron 3953 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: 0.9743. Min Range: -0.9743

Max Act: 0.9743. Min Act: -0.0000

Data Index: 1486539 (The Pile)

Max Activating Token Index: 796

Text #1

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.7113. Min Act: -0.0000

Data Index: 1676004 (The Pile)

Max Activating Token Index: 644

Text #2

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.8347. Min Act: -0.0000

Data Index: 1455573 (The Pile)

Max Activating Token Index: 67

Text #3

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.7675. Min Act: -0.0000

Data Index: 83309 (The Pile)

Max Activating Token Index: 928

Text #4

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1417705 (The Pile)

Max Activating Token Index: 830

Text #5

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.9144. Min Act: -0.0000

Data Index: 1963483 (The Pile)

Max Activating Token Index: 665

Text #6

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.7544. Min Act: -0.0000

Data Index: 597744 (The Pile)

Max Activating Token Index: 80

Text #7

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1313928 (The Pile)

Max Activating Token Index: 126

Text #8

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.7196. Min Act: -0.0000

Data Index: 82438 (The Pile)

Max Activating Token Index: 687

Text #9

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1277151 (The Pile)

Max Activating Token Index: 743

Text #10

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.6467. Min Act: -0.0000

Data Index: 410846 (The Pile)

Max Activating Token Index: 483

Text #11

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1581119 (The Pile)

Max Activating Token Index: 191

Text #12

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.6129. Min Act: -0.0000

Data Index: 743442 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.5555. Min Act: -0.0000

Data Index: 1959972 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.6192. Min Act: -0.0000

Data Index: 749326 (The Pile)

Max Activating Token Index: 341

Text #15

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.6120. Min Act: -0.0000

Data Index: 288931 (The Pile)

Max Activating Token Index: 211

Text #16

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1026145 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1677072 (The Pile)

Max Activating Token Index: 887

Text #18

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1619674 (The Pile)

Max Activating Token Index: 119

Text #19

Max Range: 0.9743. Min Range: -0.9743

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1948733 (The Pile)

Max Activating Token Index: 564