< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 5 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2620. Min Act: -0.0001

Data Index: 329170 (The Pile)

Max Activating Token Index: 382

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.2476. Min Act: -0.0001

Data Index: 311622 (The Pile)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0794. Min Act: -0.0001

Data Index: 45905 (The Pile)

Max Activating Token Index: 157

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0841. Min Act: -0.0001

Data Index: 223149 (The Pile)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0817. Min Act: -0.0001

Data Index: 1073185 (The Pile)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0808. Min Act: -0.0001

Data Index: 1538135 (The Pile)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0836. Min Act: -0.0001

Data Index: 184013 (The Pile)

Max Activating Token Index: 142

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0803. Min Act: -0.0001

Data Index: 700018 (The Pile)

Max Activating Token Index: 49

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0723. Min Act: -0.0001

Data Index: 32890 (The Pile)

Max Activating Token Index: 75

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1721959 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0819. Min Act: -0.0001

Data Index: 1696590 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0763. Min Act: -0.0001

Data Index: 8976 (The Pile)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0807. Min Act: -0.0001

Data Index: 1956410 (The Pile)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0814. Min Act: -0.0001

Data Index: 1616263 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1399313 (The Pile)

Max Activating Token Index: 161

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0780. Min Act: -0.0001

Data Index: 617771 (The Pile)

Max Activating Token Index: 131

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0816. Min Act: -0.0001

Data Index: 137228 (The Pile)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1520551 (The Pile)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1914198 (The Pile)

Max Activating Token Index: 502

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.2620. Min Range: -0.2620

Max Act: 0.0775. Min Act: -0.0001

Data Index: 359548 (The Pile)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #19