< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4079 in Layer 14

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.4743. Min Act: -0.1700

Data Index: 3054806 (The Pile)

Max Activating Token Index: 497

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.4586. Min Act: -0.1700

Data Index: 981890 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.4429. Min Act: -0.1700

Data Index: 4170000 (The Pile)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.4429. Min Act: -0.1700

Data Index: 9538544 (The Pile)

Max Activating Token Index: 866

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.4115. Min Act: -0.1700

Data Index: 6180326 (The Pile)

Max Activating Token Index: 154

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.3802. Min Act: -0.1700

Data Index: 6880997 (The Pile)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.3802. Min Act: -0.1700

Data Index: 10236776 (The Pile)

Max Activating Token Index: 680

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.3645. Min Act: -0.1700

Data Index: 10004730 (The Pile)

Max Activating Token Index: 493

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.3645. Min Act: -0.1700

Data Index: 7358016 (The Pile)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.3645. Min Act: -0.1700

Data Index: 1125523 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.3488. Min Act: -0.1700

Data Index: 9887854 (The Pile)

Max Activating Token Index: 34

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.3488. Min Act: -0.1700

Data Index: 4219769 (The Pile)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.3488. Min Act: -0.1700

Data Index: 6583335 (The Pile)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.3331. Min Act: -0.1700

Data Index: 8581065 (The Pile)

Max Activating Token Index: 367

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.3331. Min Act: -0.1700

Data Index: 4396361 (The Pile)

Max Activating Token Index: 164

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.3174. Min Act: -0.1700

Data Index: 9882638 (The Pile)

Max Activating Token Index: 394

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.3174. Min Act: -0.1700

Data Index: 6797108 (The Pile)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.3174. Min Act: -0.1700

Data Index: 1998156 (The Pile)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.3017. Min Act: -0.1700

Data Index: 4102759 (The Pile)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4743. Min Range: -3.4743

Max Act: 3.3017. Min Act: -0.1700

Data Index: 2201145 (The Pile)

Max Activating Token Index: 398

Click toggle to see full text

Truncated

Full Text #19