< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1097 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1939. Min Act: -0.1700

Data Index: 366705 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1939. Min Act: -0.1700

Data Index: 2437354 (The Pile)

Max Activating Token Index: 291

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1782. Min Act: -0.1700

Data Index: 4368061 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1624. Min Act: -0.1700

Data Index: 7039540 (The Pile)

Max Activating Token Index: 969

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1624. Min Act: -0.1700

Data Index: 1066800 (The Pile)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1467. Min Act: -0.1700

Data Index: 1162582 (The Pile)

Max Activating Token Index: 898

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1152. Min Act: -0.1700

Data Index: 6885687 (The Pile)

Max Activating Token Index: 776

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1152. Min Act: -0.1700

Data Index: 9953598 (The Pile)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1309. Min Act: -0.1700

Data Index: 852718 (The Pile)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1782. Min Act: -0.1700

Data Index: 5748021 (The Pile)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1624. Min Act: -0.1700

Data Index: 752175 (The Pile)

Max Activating Token Index: 912

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.0994. Min Act: -0.1700

Data Index: 742755 (The Pile)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1467. Min Act: -0.1700

Data Index: 9941134 (The Pile)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1782. Min Act: -0.1700

Data Index: 9520945 (The Pile)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1309. Min Act: -0.1700

Data Index: 9014610 (The Pile)

Max Activating Token Index: 930

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1309. Min Act: -0.1700

Data Index: 7956025 (The Pile)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1309. Min Act: -0.1700

Data Index: 3241023 (The Pile)

Max Activating Token Index: 848

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1309. Min Act: -0.1700

Data Index: 2176028 (The Pile)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1309. Min Act: -0.1700

Data Index: 3170968 (The Pile)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1939. Min Range: -3.1939

Max Act: 3.1309. Min Act: -0.1700

Data Index: 856523 (The Pile)

Max Activating Token Index: 787

Click toggle to see full text

Truncated

Full Text #19