< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 3070 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 3.0042. Min Range: -3.0042

Max Act: 3.0042. Min Act: -0.1700

Data Index: 9102567 (The Pile)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.9884. Min Act: -0.1700

Data Index: 8664787 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.9409. Min Act: -0.1700

Data Index: 2113635 (The Pile)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.9409. Min Act: -0.1700

Data Index: 64855 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.9092. Min Act: -0.1700

Data Index: 2418259 (The Pile)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.8934. Min Act: -0.1700

Data Index: 3543557 (The Pile)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.8934. Min Act: -0.1700

Data Index: 1086160 (The Pile)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.8775. Min Act: -0.1700

Data Index: 5842776 (The Pile)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.8616. Min Act: -0.1700

Data Index: 8235586 (The Pile)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.8457. Min Act: -0.1700

Data Index: 8613957 (The Pile)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.8298. Min Act: -0.1700

Data Index: 4686537 (The Pile)

Max Activating Token Index: 239

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.8298. Min Act: -0.1700

Data Index: 6828518 (The Pile)

Max Activating Token Index: 135

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.8298. Min Act: -0.1700

Data Index: 6496379 (The Pile)

Max Activating Token Index: 966

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.8139. Min Act: -0.1700

Data Index: 9130448 (The Pile)

Max Activating Token Index: 549

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.8139. Min Act: -0.1700

Data Index: 9887367 (The Pile)

Max Activating Token Index: 686

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.7980. Min Act: -0.1700

Data Index: 829041 (The Pile)

Max Activating Token Index: 607

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.7980. Min Act: -0.1700

Data Index: 10093547 (The Pile)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.7980. Min Act: -0.1700

Data Index: 3819460 (The Pile)

Max Activating Token Index: 652

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.7980. Min Act: -0.1700

Data Index: 10371043 (The Pile)

Max Activating Token Index: 849

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0042. Min Range: -3.0042

Max Act: 2.7820. Min Act: -0.1700

Data Index: 2154085 (The Pile)

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #19