< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1998 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.0270. Min Range: -3.0270

Max Act: 3.0270. Min Act: -0.1700

Data Index: 1082336 (The Pile)

Max Activating Token Index: 962

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.9637. Min Act: -0.1700

Data Index: 7780972 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.9320. Min Act: -0.1700

Data Index: 4693495 (The Pile)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.8845. Min Act: -0.1700

Data Index: 5122064 (The Pile)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.9003. Min Act: -0.1700

Data Index: 10263025 (The Pile)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.9003. Min Act: -0.1700

Data Index: 5096281 (The Pile)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.8845. Min Act: -0.1700

Data Index: 8290284 (The Pile)

Max Activating Token Index: 299

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.8845. Min Act: -0.1700

Data Index: 1107871 (The Pile)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.8845. Min Act: -0.1700

Data Index: 2491776 (The Pile)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.8686. Min Act: -0.1700

Data Index: 5141509 (The Pile)

Max Activating Token Index: 412

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.8527. Min Act: -0.1700

Data Index: 7514832 (The Pile)

Max Activating Token Index: 451

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.8527. Min Act: -0.1700

Data Index: 437792 (The Pile)

Max Activating Token Index: 139

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.8368. Min Act: -0.1700

Data Index: 3766174 (The Pile)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.8527. Min Act: -0.1700

Data Index: 4830391 (The Pile)

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.8368. Min Act: -0.1700

Data Index: 10625324 (The Pile)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.8368. Min Act: -0.1700

Data Index: 1180534 (The Pile)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.8368. Min Act: -0.1700

Data Index: 4710163 (The Pile)

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.8368. Min Act: -0.1700

Data Index: 7061922 (The Pile)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.8209. Min Act: -0.1700

Data Index: 8487314 (The Pile)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0270. Min Range: -3.0270

Max Act: 2.8368. Min Act: -0.1700

Data Index: 4149857 (The Pile)

Max Activating Token Index: 569

Click toggle to see full text

Truncated

Full Text #19