< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 41 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: 4.0152. Min Range: -4.0152

Max Act: 4.0152. Min Act: -0.0001

Data Index: 474512 (The Pile)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.9689. Min Act: -0.0001

Data Index: 824770 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.4098. Min Act: -0.0001

Data Index: 152481 (The Pile)

Max Activating Token Index: 678

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.1775. Min Act: -0.0001

Data Index: 761116 (The Pile)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.3744. Min Act: -0.0001

Data Index: 1170555 (The Pile)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.2567. Min Act: -0.0001

Data Index: 1320182 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.2085. Min Act: -0.0001

Data Index: 818724 (The Pile)

Max Activating Token Index: 391

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.2260. Min Act: -0.0001

Data Index: 806587 (The Pile)

Max Activating Token Index: 483

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.2102. Min Act: -0.0001

Data Index: 388088 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.4795. Min Act: -0.0001

Data Index: 509871 (The Pile)

Max Activating Token Index: 588

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.0449. Min Act: -0.0001

Data Index: 5681 (The Pile)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.1862. Min Act: -0.0001

Data Index: 1078590 (The Pile)

Max Activating Token Index: 267

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.0107. Min Act: -0.0001

Data Index: 1913419 (The Pile)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.1297. Min Act: -0.0001

Data Index: 2203 (The Pile)

Max Activating Token Index: 547

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.0152. Min Range: -4.0152

Max Act: 2.8861. Min Act: -0.0001

Data Index: 1985770 (The Pile)

Max Activating Token Index: 282

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.0152. Min Range: -4.0152

Max Act: 2.8682. Min Act: -0.0001

Data Index: 1112614 (The Pile)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.0154. Min Act: -0.0001

Data Index: 1239817 (The Pile)

Max Activating Token Index: 393

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.0152. Min Range: -4.0152

Max Act: 2.8446. Min Act: -0.0001

Data Index: 1828795 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.1123. Min Act: -0.0001

Data Index: 350328 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.0152. Min Range: -4.0152

Max Act: 3.0815. Min Act: -0.0001

Data Index: 1569926 (The Pile)

Max Activating Token Index: 553

Click toggle to see full text

Truncated

Full Text #19