< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 3009 in Layer 4

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: 2.4893. Min Range: -2.4893

Max Act: 2.4893. Min Act: -0.1700

Data Index: 2025185 (Open Web Text)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.4708. Min Act: -0.1700

Data Index: 8109451 (Open Web Text)

Max Activating Token Index: 277

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.4643. Min Act: -0.1700

Data Index: 5366369 (Open Web Text)

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.4609. Min Act: -0.1700

Data Index: 3129860 (Open Web Text)

Max Activating Token Index: 554

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.4439. Min Act: -0.1700

Data Index: 1498216 (Open Web Text)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.4410. Min Act: -0.1700

Data Index: 4355889 (Open Web Text)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.4398. Min Act: -0.1700

Data Index: 7777046 (Open Web Text)

Max Activating Token Index: 39

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.4243. Min Act: -0.1700

Data Index: 6568317 (Open Web Text)

Max Activating Token Index: 259

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.4178. Min Act: -0.1700

Data Index: 2914796 (Open Web Text)

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.4214. Min Act: -0.1700

Data Index: 1446812 (Open Web Text)

Max Activating Token Index: 139

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.3962. Min Act: -0.1700

Data Index: 8548472 (Open Web Text)

Max Activating Token Index: 849

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.4027. Min Act: -0.1700

Data Index: 7099645 (Open Web Text)

Max Activating Token Index: 524

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.4091. Min Act: -0.1700

Data Index: 5419417 (Open Web Text)

Max Activating Token Index: 419

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.3859. Min Act: -0.1700

Data Index: 240323 (Open Web Text)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.3990. Min Act: -0.1700

Data Index: 4969996 (Open Web Text)

Max Activating Token Index: 606

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.4008. Min Act: -0.1700

Data Index: 1755501 (Open Web Text)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.4033. Min Act: -0.1700

Data Index: 157409 (Open Web Text)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.3986. Min Act: -0.1700

Data Index: 1874605 (Open Web Text)

Max Activating Token Index: 654

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.3926. Min Act: -0.1700

Data Index: 70658 (Open Web Text)

Max Activating Token Index: 327

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.4893. Min Range: -2.4893

Max Act: 2.3749. Min Act: -0.1700

Data Index: 3308237 (Open Web Text)

Max Activating Token Index: 102

Click toggle to see full text

Truncated

Full Text #19