< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 57 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.5823. Min Range: -2.5823

Max Act: 2.5823. Min Act: -0.0001

Data Index: 1484619 (The Pile)

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.5823. Min Range: -2.5823

Max Act: 2.4162. Min Act: -0.0001

Data Index: 1450815 (The Pile)

Max Activating Token Index: 930

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.5823. Min Range: -2.5823

Max Act: 2.0701. Min Act: -0.0001

Data Index: 76333 (The Pile)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.9619. Min Act: -0.0001

Data Index: 1542297 (The Pile)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.8797. Min Act: -0.0001

Data Index: 1766840 (The Pile)

Max Activating Token Index: 826

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.9097. Min Act: -0.0001

Data Index: 919098 (The Pile)

Max Activating Token Index: 597

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.9080. Min Act: -0.0001

Data Index: 1815306 (The Pile)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.8264. Min Act: -0.0001

Data Index: 1737223 (The Pile)

Max Activating Token Index: 686

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.9646. Min Act: -0.0001

Data Index: 1693872 (The Pile)

Max Activating Token Index: 524

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.5823. Min Range: -2.5823

Max Act: 2.1131. Min Act: -0.0001

Data Index: 1054832 (The Pile)

Max Activating Token Index: 1015

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.9108. Min Act: -0.0001

Data Index: 1495411 (The Pile)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.7700. Min Act: -0.0001

Data Index: 1610085 (The Pile)

Max Activating Token Index: 219

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.9021. Min Act: -0.0001

Data Index: 895560 (The Pile)

Max Activating Token Index: 723

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.9070. Min Act: -0.0001

Data Index: 1214030 (The Pile)

Max Activating Token Index: 179

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.7690. Min Act: -0.0001

Data Index: 449899 (The Pile)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.7395. Min Act: -0.0001

Data Index: 993301 (The Pile)

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.8673. Min Act: -0.0001

Data Index: 1357288 (The Pile)

Max Activating Token Index: 245

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.6889. Min Act: -0.0001

Data Index: 193791 (The Pile)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.8226. Min Act: -0.0001

Data Index: 1928637 (The Pile)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.5823. Min Range: -2.5823

Max Act: 1.6084. Min Act: -0.0001

Data Index: 431297 (The Pile)

Max Activating Token Index: 516

Click toggle to see full text

Truncated

Full Text #19