< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 56 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')



Text #0

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1303. Min Act: -0.0004

Data Index: 1869489 (The Pile)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1244. Min Act: -0.0004

Data Index: 1897480 (The Pile)

Max Activating Token Index: 404

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1207. Min Act: -0.0004

Data Index: 175932 (The Pile)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1174. Min Act: -0.0004

Data Index: 133013 (The Pile)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1157. Min Act: -0.0004

Data Index: 1659321 (The Pile)

Max Activating Token Index: 920

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1160. Min Act: -0.0004

Data Index: 362787 (The Pile)

Max Activating Token Index: 366

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1161. Min Act: -0.0004

Data Index: 1220626 (The Pile)

Max Activating Token Index: 734

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1134. Min Act: -0.0004

Data Index: 413790 (The Pile)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1073. Min Act: -0.0004

Data Index: 730144 (The Pile)

Max Activating Token Index: 48

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.0999. Min Act: -0.0004

Data Index: 1838875 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1101. Min Act: -0.0004

Data Index: 837853 (The Pile)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1069. Min Act: -0.0004

Data Index: 671505 (The Pile)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1080. Min Act: -0.0004

Data Index: 1624355 (The Pile)

Max Activating Token Index: 540

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1059. Min Act: -0.0004

Data Index: 1370923 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1073. Min Act: -0.0004

Data Index: 1475600 (The Pile)

Max Activating Token Index: 997

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1110. Min Act: -0.0004

Data Index: 1229083 (The Pile)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1029. Min Act: -0.0004

Data Index: 110512 (The Pile)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1051. Min Act: -0.0004

Data Index: 559502 (The Pile)

Max Activating Token Index: 382

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1023. Min Act: -0.0004

Data Index: 1932993 (The Pile)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1303. Min Range: -0.1303

Max Act: 0.1052. Min Act: -0.0004

Data Index: 517118 (The Pile)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #19