< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 37 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2808. Min Act: -0.0001

Data Index: 1874679 (The Pile)

Max Activating Token Index: 916

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2465. Min Act: -0.0001

Data Index: 395984 (The Pile)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2880. Min Act: -0.0001

Data Index: 993941 (The Pile)

Max Activating Token Index: 73

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2648. Min Act: -0.0001

Data Index: 635326 (The Pile)

Max Activating Token Index: 203

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2771. Min Act: -0.0001

Data Index: 1674845 (The Pile)

Max Activating Token Index: 745

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2777. Min Act: -0.0001

Data Index: 612467 (The Pile)

Max Activating Token Index: 168

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2561. Min Act: -0.0001

Data Index: 1292103 (The Pile)

Max Activating Token Index: 304

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2298. Min Act: -0.0001

Data Index: 1523829 (The Pile)

Max Activating Token Index: 877

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2781. Min Act: -0.0001

Data Index: 1929139 (The Pile)

Max Activating Token Index: 244

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2602. Min Act: -0.0001

Data Index: 747285 (The Pile)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2225. Min Act: -0.0001

Data Index: 1343354 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2574. Min Act: -0.0001

Data Index: 909375 (The Pile)

Max Activating Token Index: 241

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2337. Min Act: -0.0001

Data Index: 353545 (The Pile)

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2400. Min Act: -0.0001

Data Index: 871727 (The Pile)

Max Activating Token Index: 438

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2046. Min Act: -0.0001

Data Index: 608228 (The Pile)

Max Activating Token Index: 883

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2339. Min Act: -0.0001

Data Index: 340107 (The Pile)

Max Activating Token Index: 482

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2182. Min Act: -0.0001

Data Index: 1324799 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2285. Min Act: -0.0001

Data Index: 704792 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2195. Min Act: -0.0001

Data Index: 65468 (The Pile)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2880. Min Range: -0.2880

Max Act: 0.2153. Min Act: -0.0001

Data Index: 987580 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #19