< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1796 in Layer 0

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: 2.4248. Min Range: -2.4248

Max Act: 2.4248. Min Act: -0.1700

Data Index: 7909535 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3940. Min Act: -0.1700

Data Index: 3734062 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3684. Min Act: -0.1700

Data Index: 2719920 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3719. Min Act: -0.1700

Data Index: 2500200 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3764. Min Act: -0.1700

Data Index: 5468161 (Open Web Text)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3770. Min Act: -0.1700

Data Index: 7652619 (Open Web Text)

Max Activating Token Index: 1015

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3760. Min Act: -0.1700

Data Index: 1506387 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3812. Min Act: -0.1700

Data Index: 2361861 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3712. Min Act: -0.1700

Data Index: 4189360 (Open Web Text)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3558. Min Act: -0.1700

Data Index: 2777428 (Open Web Text)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3617. Min Act: -0.1700

Data Index: 8470604 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3690. Min Act: -0.1700

Data Index: 8367278 (Open Web Text)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3521. Min Act: -0.1700

Data Index: 7838040 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3517. Min Act: -0.1700

Data Index: 1192492 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3581. Min Act: -0.1700

Data Index: 2088667 (Open Web Text)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3478. Min Act: -0.1700

Data Index: 5309424 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3478. Min Act: -0.1700

Data Index: 1009844 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3335. Min Act: -0.1700

Data Index: 5649072 (Open Web Text)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3495. Min Act: -0.1700

Data Index: 2671961 (Open Web Text)

Max Activating Token Index: 9

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.4248. Min Range: -2.4248

Max Act: 2.3389. Min Act: -0.1700

Data Index: 396427 (Open Web Text)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #19