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

Dataset: The Pile

Neuron 2729 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1532810 (The Pile)

Max Activating Token Index: 357

Text #1

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6391. Min Act: -0.0000

Data Index: 660908 (The Pile)

Max Activating Token Index: 707

Text #2

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.7291. Min Act: -0.0000

Data Index: 1557244 (The Pile)

Max Activating Token Index: 126

Text #3

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1147680 (The Pile)

Max Activating Token Index: 484

Text #4

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.8329. Min Act: -0.0000

Data Index: 203659 (The Pile)

Max Activating Token Index: 864

Text #5

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.7003. Min Act: -0.0000

Data Index: 9601 (The Pile)

Max Activating Token Index: 856

Text #6

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6181. Min Act: -0.0000

Data Index: 92433 (The Pile)

Max Activating Token Index: 445

Text #7

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6522. Min Act: -0.0000

Data Index: 1236802 (The Pile)

Max Activating Token Index: 561

Text #8

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6120. Min Act: -0.0000

Data Index: 945996 (The Pile)

Max Activating Token Index: 114

Text #9

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6522. Min Act: -0.0000

Data Index: 830523 (The Pile)

Max Activating Token Index: 329

Text #10

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1226032 (The Pile)

Max Activating Token Index: 752

Text #11

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1231818 (The Pile)

Max Activating Token Index: 781

Text #12

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.5880. Min Act: -0.0000

Data Index: 1422094 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6484. Min Act: -0.0000

Data Index: 747969 (The Pile)

Max Activating Token Index: 659

Text #14

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6409. Min Act: -0.0000

Data Index: 5368 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1624087 (The Pile)

Max Activating Token Index: 505

Text #16

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6607. Min Act: -0.0000

Data Index: 412269 (The Pile)

Max Activating Token Index: 282

Text #17

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.5918. Min Act: -0.0000

Data Index: 53769 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6047. Min Act: -0.0000

Data Index: 50009 (The Pile)

Max Activating Token Index: 940

Text #19

Max Range: 0.8329. Min Range: -0.8329

Max Act: 0.6675. Min Act: -0.0000

Data Index: 841411 (The Pile)

Max Activating Token Index: 625