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

Dataset: The Pile

Neuron 4599 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: 0.7145. Min Range: -0.7145

Max Act: 0.7145. Min Act: -0.0000

Data Index: 1657278 (The Pile)

Max Activating Token Index: 631

Text #1

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.5731. Min Act: -0.0000

Data Index: 21212 (The Pile)

Max Activating Token Index: 756

Text #2

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1639463 (The Pile)

Max Activating Token Index: 676

Text #3

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.5760. Min Act: -0.0000

Data Index: 464343 (The Pile)

Max Activating Token Index: 716

Text #4

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.5884. Min Act: -0.0000

Data Index: 439834 (The Pile)

Max Activating Token Index: 873

Text #5

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1895839 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1871736 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.5188. Min Act: -0.0000

Data Index: 869580 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.5275. Min Act: -0.0000

Data Index: 254394 (The Pile)

Max Activating Token Index: 335

Text #9

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.5010. Min Act: -0.0000

Data Index: 24730 (The Pile)

Max Activating Token Index: 1003

Text #10

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.4749. Min Act: -0.0000

Data Index: 476235 (The Pile)

Max Activating Token Index: 34

Text #11

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.4777. Min Act: -0.0000

Data Index: 951221 (The Pile)

Max Activating Token Index: 143

Text #12

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1903834 (The Pile)

Max Activating Token Index: 155

Text #13

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1406192 (The Pile)

Max Activating Token Index: 526

Text #14

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1614733 (The Pile)

Max Activating Token Index: 821

Text #15

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.4587. Min Act: -0.0000

Data Index: 749761 (The Pile)

Max Activating Token Index: 591

Text #16

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.4696. Min Act: -0.0000

Data Index: 321446 (The Pile)

Max Activating Token Index: 912

Text #17

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.4658. Min Act: -0.0000

Data Index: 940080 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.4526. Min Act: -0.0000

Data Index: 1341233 (The Pile)

Max Activating Token Index: 457

Text #19

Max Range: 0.7145. Min Range: -0.7145

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1893182 (The Pile)

Max Activating Token Index: 475