< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2013 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4955. Min Act: -0.1700

Data Index: 3546040 (Open Web Text)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4724. Min Act: -0.1700

Data Index: 8038115 (Open Web Text)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4748. Min Act: -0.1700

Data Index: 4180479 (Open Web Text)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4540. Min Act: -0.1700

Data Index: 2394375 (Open Web Text)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4609. Min Act: -0.1700

Data Index: 2633036 (Open Web Text)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4327. Min Act: -0.1700

Data Index: 2289959 (Open Web Text)

Max Activating Token Index: 25

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4452. Min Act: -0.1700

Data Index: 8487044 (Open Web Text)

Max Activating Token Index: 24

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4473. Min Act: -0.1700

Data Index: 7979309 (Open Web Text)

Max Activating Token Index: 602

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4454. Min Act: -0.1700

Data Index: 7641379 (Open Web Text)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4467. Min Act: -0.1700

Data Index: 6806647 (Open Web Text)

Max Activating Token Index: 702

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4536. Min Act: -0.1700

Data Index: 8582412 (Open Web Text)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4333. Min Act: -0.1700

Data Index: 776456 (Open Web Text)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4224. Min Act: -0.1700

Data Index: 1161579 (Open Web Text)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4271. Min Act: -0.1700

Data Index: 7093170 (Open Web Text)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4201. Min Act: -0.1700

Data Index: 1728862 (Open Web Text)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4176. Min Act: -0.1700

Data Index: 508505 (Open Web Text)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4211. Min Act: -0.1700

Data Index: 4010561 (Open Web Text)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4202. Min Act: -0.1700

Data Index: 5914683 (Open Web Text)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4180. Min Act: -0.1700

Data Index: 3815582 (Open Web Text)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.4955. Min Range: -2.4955

Max Act: 2.4282. Min Act: -0.1700

Data Index: 4430383 (Open Web Text)

Max Activating Token Index: 51

Click toggle to see full text

Truncated

Full Text #19