< Prev | Home | Model | Random | Next >

Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 4 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')



Text #0

Max Range: 2.0500. Min Range: -2.0500

Max Act: 2.0500. Min Act: -0.1700

Data Index: 8760153 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.0500. Min Range: -2.0500

Max Act: 2.0163. Min Act: -0.1700

Data Index: 6361667 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.9486. Min Act: -0.1700

Data Index: 4416450 (Open Web Text)

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.9655. Min Act: -0.1700

Data Index: 2039239 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.9486. Min Act: -0.1700

Data Index: 4139190 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.9486. Min Act: -0.1700

Data Index: 5417235 (Open Web Text)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.9486. Min Act: -0.1700

Data Index: 7601253 (Open Web Text)

Max Activating Token Index: 186

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.9316. Min Act: -0.1700

Data Index: 2814093 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.9316. Min Act: -0.1700

Data Index: 315052 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.9316. Min Act: -0.1700

Data Index: 4124713 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.8975. Min Act: -0.1700

Data Index: 8450016 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.9146. Min Act: -0.1700

Data Index: 6792229 (Open Web Text)

Max Activating Token Index: 151

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.9146. Min Act: -0.1700

Data Index: 7742204 (Open Web Text)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.9146. Min Act: -0.1700

Data Index: 7804548 (Open Web Text)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.9146. Min Act: -0.1700

Data Index: 7610299 (Open Web Text)

Max Activating Token Index: 372

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.8975. Min Act: -0.1700

Data Index: 3438265 (Open Web Text)

Max Activating Token Index: 157

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.8975. Min Act: -0.1700

Data Index: 2754785 (Open Web Text)

Max Activating Token Index: 288

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.8975. Min Act: -0.1700

Data Index: 7690478 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.8804. Min Act: -0.1700

Data Index: 7946988 (Open Web Text)

Max Activating Token Index: 179

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.0500. Min Range: -2.0500

Max Act: 1.8804. Min Act: -0.1700

Data Index: 433076 (Open Web Text)

Max Activating Token Index: 283

Click toggle to see full text

Truncated

Full Text #19