< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1792 in Layer 2

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: 2.2581. Min Range: -2.2581

Max Act: 2.2581. Min Act: -0.1698

Data Index: 2695494 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.1731. Min Act: -0.1697

Data Index: 3691971 (Open Web Text)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.1120. Min Act: -0.1696

Data Index: 7963039 (Open Web Text)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.1263. Min Act: -0.1700

Data Index: 8268099 (Open Web Text)

Max Activating Token Index: 827

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.1148. Min Act: -0.1693

Data Index: 4793606 (Open Web Text)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.1210. Min Act: -0.1699

Data Index: 422391 (Open Web Text)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.1160. Min Act: -0.1699

Data Index: 4951925 (Open Web Text)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.1267. Min Act: -0.1700

Data Index: 4595118 (Open Web Text)

Max Activating Token Index: 668

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.0890. Min Act: -0.1693

Data Index: 916432 (Open Web Text)

Max Activating Token Index: 645

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.0759. Min Act: -0.1700

Data Index: 6172500 (Open Web Text)

Max Activating Token Index: 44

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.0396. Min Act: -0.1699

Data Index: 8175132 (Open Web Text)

Max Activating Token Index: 708

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.0542. Min Act: -0.1700

Data Index: 3889564 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.0302. Min Act: -0.1700

Data Index: 4161034 (Open Web Text)

Max Activating Token Index: 765

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.0179. Min Act: -0.1699

Data Index: 1571138 (Open Web Text)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.0079. Min Act: -0.1700

Data Index: 4711294 (Open Web Text)

Max Activating Token Index: 225

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.0272. Min Act: -0.1700

Data Index: 1438077 (Open Web Text)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.0048. Min Act: -0.1697

Data Index: 8155608 (Open Web Text)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.0258. Min Act: -0.1700

Data Index: 1954847 (Open Web Text)

Max Activating Token Index: 640

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.2581. Min Range: -2.2581

Max Act: 2.0086. Min Act: -0.1700

Data Index: 802258 (Open Web Text)

Max Activating Token Index: 816

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.2581. Min Range: -2.2581

Max Act: 1.9968. Min Act: -0.1700

Data Index: 6758557 (Open Web Text)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #19