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

Dataset: The Pile

Neuron 1376 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4421. Min Range: -1.4421

Max Act: 1.4421. Min Act: -0.0000

Data Index: 1262477 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 1.4421. Min Range: -1.4421

Max Act: 1.3155. Min Act: -0.0000

Data Index: 728492 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 1.4421. Min Range: -1.4421

Max Act: 1.2516. Min Act: -0.0000

Data Index: 1529481 (The Pile)

Max Activating Token Index: 604

Text #3

Max Range: 1.4421. Min Range: -1.4421

Max Act: 1.0880. Min Act: -0.0000

Data Index: 610558 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 1.4421. Min Range: -1.4421

Max Act: 1.0379. Min Act: -0.0000

Data Index: 636898 (The Pile)

Max Activating Token Index: 851

Text #5

Max Range: 1.4421. Min Range: -1.4421

Max Act: 1.0078. Min Act: -0.0000

Data Index: 1698953 (The Pile)

Max Activating Token Index: 800

Text #6

Max Range: 1.4421. Min Range: -1.4421

Max Act: 0.9843. Min Act: -0.0000

Data Index: 80539 (The Pile)

Max Activating Token Index: 236

Text #7

Max Range: 1.4421. Min Range: -1.4421

Max Act: 1.0540. Min Act: -0.0000

Data Index: 416916 (The Pile)

Max Activating Token Index: 501

Text #8

Max Range: 1.4421. Min Range: -1.4421

Max Act: 0.9863. Min Act: -0.0000

Data Index: 533910 (The Pile)

Max Activating Token Index: 904

Text #9

Max Range: 1.4421. Min Range: -1.4421

Max Act: 0.8810. Min Act: -0.0000

Data Index: 200365 (The Pile)

Max Activating Token Index: 596

Text #10

Max Range: 1.4421. Min Range: -1.4421

Max Act: 0.9039. Min Act: -0.0000

Data Index: 1079077 (The Pile)

Max Activating Token Index: 905

Text #11

Max Range: 1.4421. Min Range: -1.4421

Max Act: 0.9556. Min Act: -0.0000

Data Index: 777486 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 1.4421. Min Range: -1.4421

Max Act: 0.8213. Min Act: -0.0000

Data Index: 920846 (The Pile)

Max Activating Token Index: 627

Text #13

Max Range: 1.4421. Min Range: -1.4421

Max Act: 0.9343. Min Act: -0.0000

Data Index: 538603 (The Pile)

Max Activating Token Index: 465

Text #14

Max Range: 1.4421. Min Range: -1.4421

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1309745 (The Pile)

Max Activating Token Index: 775

Text #15

Max Range: 1.4421. Min Range: -1.4421

Max Act: 0.8764. Min Act: -0.0000

Data Index: 1532793 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 1.4421. Min Range: -1.4421

Max Act: 0.8613. Min Act: -0.0000

Data Index: 956335 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 1.4421. Min Range: -1.4421

Max Act: 0.9046. Min Act: -0.0000

Data Index: 1467104 (The Pile)

Max Activating Token Index: 291

Text #18

Max Range: 1.4421. Min Range: -1.4421

Max Act: 0.8915. Min Act: -0.0000

Data Index: 971515 (The Pile)

Max Activating Token Index: 123

Text #19

Max Range: 1.4421. Min Range: -1.4421

Max Act: 0.8529. Min Act: -0.0000

Data Index: 1672623 (The Pile)

Max Activating Token Index: 473