< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 44 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 4.2209. Min Range: -4.2209

Max Act: 4.2209. Min Act: -0.1700

Data Index: 2286656 (The Pile)

Max Activating Token Index: 84

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.2209. Min Range: -4.2209

Max Act: 4.0959. Min Act: -0.1700

Data Index: 5537932 (The Pile)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.2209. Min Range: -4.2209

Max Act: 4.0646. Min Act: -0.1700

Data Index: 784147 (The Pile)

Max Activating Token Index: 266

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.2209. Min Range: -4.2209

Max Act: 4.0334. Min Act: -0.1700

Data Index: 9552797 (The Pile)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.2209. Min Range: -4.2209

Max Act: 4.0021. Min Act: -0.1700

Data Index: 8734530 (The Pile)

Max Activating Token Index: 289

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.2209. Min Range: -4.2209

Max Act: 4.0021. Min Act: -0.1700

Data Index: 4451295 (The Pile)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.2209. Min Range: -4.2209

Max Act: 4.0021. Min Act: -0.1700

Data Index: 7520145 (The Pile)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.2209. Min Range: -4.2209

Max Act: 3.9708. Min Act: -0.1700

Data Index: 9572600 (The Pile)

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.2209. Min Range: -4.2209

Max Act: 3.9708. Min Act: -0.1700

Data Index: 8952809 (The Pile)

Max Activating Token Index: 1006

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.2209. Min Range: -4.2209

Max Act: 3.9552. Min Act: -0.1700

Data Index: 4754365 (The Pile)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.2209. Min Range: -4.2209

Max Act: 3.9396. Min Act: -0.1700

Data Index: 7268873 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.2209. Min Range: -4.2209

Max Act: 3.9396. Min Act: -0.1700

Data Index: 9011540 (The Pile)

Max Activating Token Index: 782

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.2209. Min Range: -4.2209

Max Act: 3.9396. Min Act: -0.1700

Data Index: 5774278 (The Pile)

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.2209. Min Range: -4.2209

Max Act: 3.9239. Min Act: -0.1700

Data Index: 9895604 (The Pile)

Max Activating Token Index: 438

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.2209. Min Range: -4.2209

Max Act: 3.9239. Min Act: -0.1700

Data Index: 6608749 (The Pile)

Max Activating Token Index: 835

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.2209. Min Range: -4.2209

Max Act: 3.9239. Min Act: -0.1700

Data Index: 9640915 (The Pile)

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.2209. Min Range: -4.2209

Max Act: 3.9239. Min Act: -0.1700

Data Index: 10474734 (The Pile)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.2209. Min Range: -4.2209

Max Act: 3.9239. Min Act: -0.1700

Data Index: 3452193 (The Pile)

Max Activating Token Index: 925

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.2209. Min Range: -4.2209

Max Act: 3.9083. Min Act: -0.1700

Data Index: 7950528 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.2209. Min Range: -4.2209

Max Act: 3.9083. Min Act: -0.1700

Data Index: 3765611 (The Pile)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #19