< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1149 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: 3.4267. Min Range: -3.4267

Max Act: 3.4267. Min Act: -0.1700

Data Index: 2441402 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.3953. Min Act: -0.1700

Data Index: 5338991 (The Pile)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.3639. Min Act: -0.1700

Data Index: 3788448 (The Pile)

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.3325. Min Act: -0.1700

Data Index: 5155624 (The Pile)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.3325. Min Act: -0.1700

Data Index: 7770415 (The Pile)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.3011. Min Act: -0.1700

Data Index: 719351 (The Pile)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.3325. Min Act: -0.1700

Data Index: 9370086 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.3011. Min Act: -0.1700

Data Index: 7471094 (The Pile)

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.3325. Min Act: -0.1700

Data Index: 930404 (The Pile)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.3011. Min Act: -0.1700

Data Index: 180557 (The Pile)

Max Activating Token Index: 460

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.3011. Min Act: -0.1700

Data Index: 6099941 (The Pile)

Max Activating Token Index: 199

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.3168. Min Act: -0.1700

Data Index: 6487176 (The Pile)

Max Activating Token Index: 646

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.3168. Min Act: -0.1700

Data Index: 5509268 (The Pile)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.2854. Min Act: -0.1700

Data Index: 6890682 (The Pile)

Max Activating Token Index: 668

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.2854. Min Act: -0.1700

Data Index: 7305044 (The Pile)

Max Activating Token Index: 379

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.2540. Min Act: -0.1700

Data Index: 4267822 (The Pile)

Max Activating Token Index: 328

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.2854. Min Act: -0.1700

Data Index: 7777235 (The Pile)

Max Activating Token Index: 962

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.2383. Min Act: -0.1700

Data Index: 9331338 (The Pile)

Max Activating Token Index: 66

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.2540. Min Act: -0.1700

Data Index: 6420197 (The Pile)

Max Activating Token Index: 866

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4267. Min Range: -3.4267

Max Act: 3.2383. Min Act: -0.1700

Data Index: 8537415 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #19