< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 3051 in Layer 3

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: 2.3904. Min Range: -2.3904

Max Act: 2.3904. Min Act: -0.1700

Data Index: 6603589 (Open Web Text)

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.3738. Min Act: -0.1700

Data Index: 8242696 (Open Web Text)

Max Activating Token Index: 320

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.3632. Min Act: -0.1700

Data Index: 6160946 (Open Web Text)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.3169. Min Act: -0.1700

Data Index: 1049793 (Open Web Text)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.3049. Min Act: -0.1700

Data Index: 7882687 (Open Web Text)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.2955. Min Act: -0.1700

Data Index: 1071311 (Open Web Text)

Max Activating Token Index: 914

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.2829. Min Act: -0.1700

Data Index: 3723280 (Open Web Text)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.2550. Min Act: -0.1700

Data Index: 124287 (Open Web Text)

Max Activating Token Index: 446

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.2712. Min Act: -0.1700

Data Index: 6100023 (Open Web Text)

Max Activating Token Index: 571

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.2825. Min Act: -0.1700

Data Index: 6020365 (Open Web Text)

Max Activating Token Index: 99

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.2693. Min Act: -0.1700

Data Index: 7536406 (Open Web Text)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.2624. Min Act: -0.1700

Data Index: 1843985 (Open Web Text)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.2699. Min Act: -0.1700

Data Index: 7294406 (Open Web Text)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.2603. Min Act: -0.1700

Data Index: 317486 (Open Web Text)

Max Activating Token Index: 927

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.2793. Min Act: -0.1700

Data Index: 324936 (Open Web Text)

Max Activating Token Index: 800

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.2493. Min Act: -0.1700

Data Index: 1024729 (Open Web Text)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.2568. Min Act: -0.1700

Data Index: 2554590 (Open Web Text)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.2390. Min Act: -0.1700

Data Index: 3784915 (Open Web Text)

Max Activating Token Index: 549

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.2251. Min Act: -0.1700

Data Index: 7358990 (Open Web Text)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.3904. Min Range: -2.3904

Max Act: 2.2570. Min Act: -0.1700

Data Index: 3498378 (Open Web Text)

Max Activating Token Index: 471

Click toggle to see full text

Truncated

Full Text #19