< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5064 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.3593. Min Act: -0.0000

Data Index: 953186 (The Pile)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.2609. Min Act: -0.0000

Data Index: 320552 (The Pile)

Max Activating Token Index: 411

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.0939. Min Act: -0.0000

Data Index: 811413 (The Pile)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.3593. Min Range: -3.3593

Max Act: 3.1881. Min Act: -0.0000

Data Index: 168117 (The Pile)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.9621. Min Act: -0.0000

Data Index: 892983 (The Pile)

Max Activating Token Index: 422

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.5903. Min Act: -0.0000

Data Index: 1063811 (The Pile)

Max Activating Token Index: 693

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.5691. Min Act: -0.0000

Data Index: 1808543 (The Pile)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.8081. Min Act: -0.0000

Data Index: 1050606 (The Pile)

Max Activating Token Index: 50

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.5014. Min Act: -0.0000

Data Index: 1733477 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.7003. Min Act: -0.0000

Data Index: 453503 (The Pile)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.5836. Min Act: -0.0000

Data Index: 1577173 (The Pile)

Max Activating Token Index: 58

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.6406. Min Act: -0.0000

Data Index: 1240204 (The Pile)

Max Activating Token Index: 57

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.5822. Min Act: -0.0000

Data Index: 1042796 (The Pile)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.5638. Min Act: -0.0000

Data Index: 137961 (The Pile)

Max Activating Token Index: 216

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.5510. Min Act: -0.0000

Data Index: 644884 (The Pile)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.3467. Min Act: -0.0000

Data Index: 1006351 (The Pile)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.4591. Min Act: -0.0000

Data Index: 1294531 (The Pile)

Max Activating Token Index: 442

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.3318. Min Act: -0.0000

Data Index: 1120688 (The Pile)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.4453. Min Act: -0.0000

Data Index: 252298 (The Pile)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.3593. Min Range: -3.3593

Max Act: 2.3088. Min Act: -0.0000

Data Index: 286499 (The Pile)

Max Activating Token Index: 408

Click toggle to see full text

Truncated

Full Text #19