< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2407 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1353. Min Act: -0.0002

Data Index: 1990416 (The Pile)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1212. Min Act: -0.0002

Data Index: 561727 (The Pile)

Max Activating Token Index: 209

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1442. Min Act: -0.0002

Data Index: 878088 (The Pile)

Max Activating Token Index: 915

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1162. Min Act: -0.0002

Data Index: 944868 (The Pile)

Max Activating Token Index: 495

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1049. Min Act: -0.0002

Data Index: 526897 (The Pile)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1436721 (The Pile)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.1060. Min Act: -0.0002

Data Index: 1487481 (The Pile)

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1725201 (The Pile)

Max Activating Token Index: 546

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0938. Min Act: -0.0002

Data Index: 865201 (The Pile)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0921. Min Act: -0.0002

Data Index: 802623 (The Pile)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0944. Min Act: -0.0002

Data Index: 910429 (The Pile)

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1111819 (The Pile)

Max Activating Token Index: 331

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1189141 (The Pile)

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0910. Min Act: -0.0002

Data Index: 184282 (The Pile)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0877. Min Act: -0.0002

Data Index: 1618294 (The Pile)

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0843. Min Act: -0.0002

Data Index: 133109 (The Pile)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1438297 (The Pile)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1332525 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1739224 (The Pile)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1442. Min Range: -0.1442

Max Act: 0.0783. Min Act: -0.0002

Data Index: 415167 (The Pile)

Max Activating Token Index: 88

Click toggle to see full text

Truncated

Full Text #19