< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 64 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.3268. Min Act: -0.0001

Data Index: 297282 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2904. Min Act: -0.0001

Data Index: 123060 (The Pile)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2892. Min Act: -0.0001

Data Index: 1582176 (The Pile)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2823. Min Act: -0.0001

Data Index: 1104123 (The Pile)

Max Activating Token Index: 477

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2884. Min Act: -0.0001

Data Index: 142335 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2933. Min Act: -0.0001

Data Index: 268367 (The Pile)

Max Activating Token Index: 270

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2865. Min Act: -0.0001

Data Index: 550210 (The Pile)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2038. Min Act: -0.0001

Data Index: 1612825 (The Pile)

Max Activating Token Index: 175

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2690. Min Act: -0.0001

Data Index: 493997 (The Pile)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2700. Min Act: -0.0001

Data Index: 145345 (The Pile)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2636. Min Act: -0.0001

Data Index: 318722 (The Pile)

Max Activating Token Index: 218

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2718. Min Act: -0.0001

Data Index: 403922 (The Pile)

Max Activating Token Index: 323

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2635. Min Act: -0.0001

Data Index: 569821 (The Pile)

Max Activating Token Index: 748

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2666. Min Act: -0.0001

Data Index: 1847112 (The Pile)

Max Activating Token Index: 836

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2470. Min Act: -0.0001

Data Index: 573839 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2455. Min Act: -0.0001

Data Index: 1253065 (The Pile)

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2615. Min Act: -0.0001

Data Index: 1588094 (The Pile)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2437. Min Act: -0.0001

Data Index: 251986 (The Pile)

Max Activating Token Index: 32

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2487. Min Act: -0.0001

Data Index: 1936043 (The Pile)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.3268. Min Range: -0.3268

Max Act: 0.2569. Min Act: -0.0001

Data Index: 926920 (The Pile)

Max Activating Token Index: 184

Click toggle to see full text

Truncated

Full Text #19