< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 74 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: 1.0776. Min Range: -1.0776

Max Act: 1.0776. Min Act: -0.0001

Data Index: 1804507 (The Pile)

Max Activating Token Index: 154

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.0776. Min Range: -1.0776

Max Act: 1.0179. Min Act: -0.0001

Data Index: 454952 (The Pile)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.8998. Min Act: -0.0001

Data Index: 156995 (The Pile)

Max Activating Token Index: 597

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.8981. Min Act: -0.0001

Data Index: 441789 (The Pile)

Max Activating Token Index: 900

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.9702. Min Act: -0.0001

Data Index: 616764 (The Pile)

Max Activating Token Index: 746

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.9196. Min Act: -0.0001

Data Index: 621092 (The Pile)

Max Activating Token Index: 185

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.9512. Min Act: -0.0001

Data Index: 1690358 (The Pile)

Max Activating Token Index: 174

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.9165. Min Act: -0.0001

Data Index: 1154040 (The Pile)

Max Activating Token Index: 227

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.8666. Min Act: -0.0001

Data Index: 17177 (The Pile)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.8926. Min Act: -0.0001

Data Index: 684805 (The Pile)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.8334. Min Act: -0.0001

Data Index: 772959 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.9056. Min Act: -0.0001

Data Index: 651846 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.8532. Min Act: -0.0001

Data Index: 966929 (The Pile)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.9308. Min Act: -0.0001

Data Index: 1435564 (The Pile)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.9231. Min Act: -0.0001

Data Index: 1951031 (The Pile)

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.7813. Min Act: -0.0001

Data Index: 1326280 (The Pile)

Max Activating Token Index: 741

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.7730. Min Act: -0.0001

Data Index: 1458666 (The Pile)

Max Activating Token Index: 979

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.8452. Min Act: -0.0001

Data Index: 1901316 (The Pile)

Max Activating Token Index: 681

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.8095. Min Act: -0.0001

Data Index: 1797365 (The Pile)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.0776. Min Range: -1.0776

Max Act: 0.8706. Min Act: -0.0001

Data Index: 1933480 (The Pile)

Max Activating Token Index: 481

Click toggle to see full text

Truncated

Full Text #19