< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2560 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: 2.8677. Min Range: -2.8677

Max Act: 2.8677. Min Act: -0.1700

Data Index: 8457446 (Open Web Text)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.8273. Min Act: -0.1700

Data Index: 6367784 (Open Web Text)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.7661. Min Act: -0.1700

Data Index: 8425784 (Open Web Text)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.7762. Min Act: -0.1700

Data Index: 8425781 (Open Web Text)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.7484. Min Act: -0.1700

Data Index: 2645350 (Open Web Text)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.7596. Min Act: -0.1700

Data Index: 8425791 (Open Web Text)

Max Activating Token Index: 61

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.7310. Min Act: -0.1700

Data Index: 1082034 (Open Web Text)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.7183. Min Act: -0.1700

Data Index: 8425783 (Open Web Text)

Max Activating Token Index: 507

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.7389. Min Act: -0.1700

Data Index: 1298523 (Open Web Text)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.7364. Min Act: -0.1700

Data Index: 1073262 (Open Web Text)

Max Activating Token Index: 806

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.7345. Min Act: -0.1700

Data Index: 7409664 (Open Web Text)

Max Activating Token Index: 192

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.7043. Min Act: -0.1700

Data Index: 8425793 (Open Web Text)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.7241. Min Act: -0.1700

Data Index: 8425786 (Open Web Text)

Max Activating Token Index: 319

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.7099. Min Act: -0.1700

Data Index: 8425782 (Open Web Text)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.7021. Min Act: -0.1700

Data Index: 8425788 (Open Web Text)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.6779. Min Act: -0.1700

Data Index: 1858058 (Open Web Text)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.6716. Min Act: -0.1700

Data Index: 7600221 (Open Web Text)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.6674. Min Act: -0.1700

Data Index: 1582821 (Open Web Text)

Max Activating Token Index: 253

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.6636. Min Act: -0.1700

Data Index: 1646704 (Open Web Text)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8677. Min Range: -2.8677

Max Act: 2.6602. Min Act: -0.1700

Data Index: 1567886 (Open Web Text)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #19