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

Dataset: The Pile

Neuron 4426 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: 0.7641. Min Range: -0.7641

Max Act: 0.7586. Min Act: -0.0000

Data Index: 1496214 (The Pile)

Max Activating Token Index: 227

Text #1

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.7641. Min Act: -0.0000

Data Index: 1342208 (The Pile)

Max Activating Token Index: 516

Text #2

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6915. Min Act: -0.0000

Data Index: 727028 (The Pile)

Max Activating Token Index: 592

Text #3

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.7077. Min Act: -0.0000

Data Index: 1919341 (The Pile)

Max Activating Token Index: 656

Text #4

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6365. Min Act: -0.0000

Data Index: 1929796 (The Pile)

Max Activating Token Index: 680

Text #5

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1246573 (The Pile)

Max Activating Token Index: 292

Text #6

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6497. Min Act: -0.0000

Data Index: 377833 (The Pile)

Max Activating Token Index: 279

Text #7

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1275416 (The Pile)

Max Activating Token Index: 674

Text #8

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1224372 (The Pile)

Max Activating Token Index: 232

Text #9

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5685. Min Act: -0.0000

Data Index: 357348 (The Pile)

Max Activating Token Index: 256

Text #10

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5933. Min Act: -0.0000

Data Index: 526632 (The Pile)

Max Activating Token Index: 747

Text #11

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1246247 (The Pile)

Max Activating Token Index: 24

Text #12

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5824. Min Act: -0.0000

Data Index: 438877 (The Pile)

Max Activating Token Index: 265

Text #13

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6459. Min Act: -0.0000

Data Index: 1979512 (The Pile)

Max Activating Token Index: 878

Text #14

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6105. Min Act: -0.0000

Data Index: 893691 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5845. Min Act: -0.0000

Data Index: 767411 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5543. Min Act: -0.0000

Data Index: 834655 (The Pile)

Max Activating Token Index: 246

Text #17

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1579732 (The Pile)

Max Activating Token Index: 912

Text #18

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.5493. Min Act: -0.0000

Data Index: 501314 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 0.7641. Min Range: -0.7641

Max Act: 0.6029. Min Act: -0.0000

Data Index: 1306505 (The Pile)

Max Activating Token Index: 789