< Prev | Home | Model | Random | Next >

Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4080 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')



Text #0

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1297. Min Act: -0.0001

Data Index: 1646929 (The Pile)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1207. Min Act: -0.0001

Data Index: 456004 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1036. Min Act: -0.0001

Data Index: 489195 (The Pile)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0987. Min Act: -0.0001

Data Index: 799144 (The Pile)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1103. Min Act: -0.0001

Data Index: 675205 (The Pile)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1122131 (The Pile)

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1174. Min Act: -0.0001

Data Index: 420224 (The Pile)

Max Activating Token Index: 696

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1115. Min Act: -0.0001

Data Index: 1751190 (The Pile)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1097. Min Act: -0.0001

Data Index: 1536882 (The Pile)

Max Activating Token Index: 717

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1075. Min Act: -0.0001

Data Index: 250840 (The Pile)

Max Activating Token Index: 578

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1122. Min Act: -0.0001

Data Index: 1025018 (The Pile)

Max Activating Token Index: 821

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1222203 (The Pile)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1098. Min Act: -0.0001

Data Index: 1791278 (The Pile)

Max Activating Token Index: 786

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1120. Min Act: -0.0001

Data Index: 1152501 (The Pile)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1008. Min Act: -0.0001

Data Index: 358286 (The Pile)

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1046. Min Act: -0.0002

Data Index: 495128 (The Pile)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1478229 (The Pile)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0997. Min Act: -0.0001

Data Index: 850234 (The Pile)

Max Activating Token Index: 179

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1833986 (The Pile)

Max Activating Token Index: 465

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1090. Min Act: -0.0001

Data Index: 601557 (The Pile)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #19