< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 10 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.9043. Min Act: -0.0001

Data Index: 469769 (The Pile)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.8539. Min Act: -0.0001

Data Index: 388981 (The Pile)

Max Activating Token Index: 578

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.9303. Min Act: -0.0001

Data Index: 601889 (The Pile)

Max Activating Token Index: 831

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.9087. Min Act: -0.0001

Data Index: 1178506 (The Pile)

Max Activating Token Index: 688

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.8641. Min Act: -0.0001

Data Index: 1657762 (The Pile)

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.7807. Min Act: -0.0001

Data Index: 1449069 (The Pile)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.7137. Min Act: -0.0001

Data Index: 1580913 (The Pile)

Max Activating Token Index: 401

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.7977. Min Act: -0.0001

Data Index: 1941222 (The Pile)

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.7012. Min Act: -0.0001

Data Index: 527788 (The Pile)

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.6460. Min Act: -0.0001

Data Index: 1541838 (The Pile)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.6300. Min Act: -0.0001

Data Index: 128353 (The Pile)

Max Activating Token Index: 150

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.7183. Min Act: -0.0001

Data Index: 1821608 (The Pile)

Max Activating Token Index: 346

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.7312. Min Act: -0.0001

Data Index: 1253506 (The Pile)

Max Activating Token Index: 139

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.6390. Min Act: -0.0001

Data Index: 1361118 (The Pile)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.6556. Min Act: -0.0001

Data Index: 1871255 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.5638. Min Act: -0.0001

Data Index: 1525901 (The Pile)

Max Activating Token Index: 131

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.5982. Min Act: -0.0001

Data Index: 955095 (The Pile)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.4519. Min Act: -0.0001

Data Index: 11875 (The Pile)

Max Activating Token Index: 516

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.4331. Min Act: -0.0001

Data Index: 1953466 (The Pile)

Max Activating Token Index: 444

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.9303. Min Range: -1.9303

Max Act: 1.4974. Min Act: -0.0001

Data Index: 1982160 (The Pile)

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #19