< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 4059 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: 1.7688. Min Range: -1.7688

Max Act: 1.6586. Min Act: -0.0001

Data Index: 1182973 (The Pile)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.7688. Min Act: -0.0001

Data Index: 186283 (The Pile)

Max Activating Token Index: 46

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.5034. Min Act: -0.0001

Data Index: 1501591 (The Pile)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.4689. Min Act: -0.0001

Data Index: 824214 (The Pile)

Max Activating Token Index: 972

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.5858. Min Act: -0.0001

Data Index: 294620 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.5717. Min Act: -0.0001

Data Index: 260115 (The Pile)

Max Activating Token Index: 234

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.5002. Min Act: -0.0001

Data Index: 1277904 (The Pile)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.3710. Min Act: -0.0001

Data Index: 1045474 (The Pile)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.3874. Min Act: -0.0001

Data Index: 1519163 (The Pile)

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.3100. Min Act: -0.0001

Data Index: 670298 (The Pile)

Max Activating Token Index: 366

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.3263. Min Act: -0.0001

Data Index: 1640502 (The Pile)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.3960. Min Act: -0.0001

Data Index: 1291096 (The Pile)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.4152. Min Act: -0.0001

Data Index: 1185391 (The Pile)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.3052. Min Act: -0.0001

Data Index: 1080941 (The Pile)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.3014. Min Act: -0.0001

Data Index: 857052 (The Pile)

Max Activating Token Index: 812

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.3407. Min Act: -0.0001

Data Index: 1720210 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.1745. Min Act: -0.0001

Data Index: 164742 (The Pile)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.2263. Min Act: -0.0001

Data Index: 302082 (The Pile)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.2573. Min Act: -0.0001

Data Index: 1481544 (The Pile)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.7688. Min Range: -1.7688

Max Act: 1.2460. Min Act: -0.0001

Data Index: 721132 (The Pile)

Max Activating Token Index: 466

Click toggle to see full text

Truncated

Full Text #19