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

Dataset: The Pile

Neuron 4300 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: 0.9894. Min Range: -0.9894

Max Act: 0.9894. Min Act: -0.0000

Data Index: 1986945 (The Pile)

Max Activating Token Index: 100

Text #1

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7118. Min Act: -0.0000

Data Index: 928893 (The Pile)

Max Activating Token Index: 720

Text #2

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7625. Min Act: -0.0000

Data Index: 982184 (The Pile)

Max Activating Token Index: 551

Text #3

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1097678 (The Pile)

Max Activating Token Index: 589

Text #4

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1443526 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.6630. Min Act: -0.0000

Data Index: 349072 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7301. Min Act: -0.0000

Data Index: 109597 (The Pile)

Max Activating Token Index: 580

Text #7

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.6456. Min Act: -0.0000

Data Index: 610934 (The Pile)

Max Activating Token Index: 809

Text #8

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1513757 (The Pile)

Max Activating Token Index: 561

Text #9

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7144. Min Act: -0.0000

Data Index: 256930 (The Pile)

Max Activating Token Index: 621

Text #10

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.6760. Min Act: -0.0000

Data Index: 380730 (The Pile)

Max Activating Token Index: 703

Text #11

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1013822 (The Pile)

Max Activating Token Index: 576

Text #12

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1689025 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.6524. Min Act: -0.0000

Data Index: 1753128 (The Pile)

Max Activating Token Index: 837

Text #14

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1848351 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.6810. Min Act: -0.0000

Data Index: 1953354 (The Pile)

Max Activating Token Index: 83

Text #16

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7280. Min Act: -0.0000

Data Index: 349375 (The Pile)

Max Activating Token Index: 762

Text #17

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.6830. Min Act: -0.0000

Data Index: 1092085 (The Pile)

Max Activating Token Index: 700

Text #18

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.7287. Min Act: -0.0000

Data Index: 301439 (The Pile)

Max Activating Token Index: 739

Text #19

Max Range: 0.9894. Min Range: -0.9894

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1189310 (The Pile)

Max Activating Token Index: 718