< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 560 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')

Text #0

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.7113. Min Act: -0.1700

Data Index: 347636 (Open Web Text)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.6665. Min Act: -0.1700

Data Index: 615251 (Open Web Text)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.6763. Min Act: -0.1700

Data Index: 7456821 (Open Web Text)

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.6397. Min Act: -0.1700

Data Index: 4330448 (Open Web Text)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.6322. Min Act: -0.1700

Data Index: 4994363 (Open Web Text)

Max Activating Token Index: 877

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.6549. Min Act: -0.1700

Data Index: 3538884 (Open Web Text)

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.6415. Min Act: -0.1700

Data Index: 8809609 (Open Web Text)

Max Activating Token Index: 447

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.6289. Min Act: -0.1700

Data Index: 6350332 (Open Web Text)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.6345. Min Act: -0.1700

Data Index: 7034132 (Open Web Text)

Max Activating Token Index: 484

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.6033. Min Act: -0.1700

Data Index: 2197715 (Open Web Text)

Max Activating Token Index: 1008

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.6040. Min Act: -0.1700

Data Index: 1923440 (Open Web Text)

Max Activating Token Index: 741

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.5867. Min Act: -0.1700

Data Index: 8445473 (Open Web Text)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.5795. Min Act: -0.1700

Data Index: 2207780 (Open Web Text)

Max Activating Token Index: 278

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.5287. Min Act: -0.1700

Data Index: 4044484 (Open Web Text)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.5859. Min Act: -0.1700

Data Index: 902110 (Open Web Text)

Max Activating Token Index: 563

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.5621. Min Act: -0.1700

Data Index: 2002767 (Open Web Text)

Max Activating Token Index: 659

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.5330. Min Act: -0.1700

Data Index: 338813 (Open Web Text)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.5532. Min Act: -0.1700

Data Index: 1859588 (Open Web Text)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.5780. Min Act: -0.1700

Data Index: 7929538 (Open Web Text)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.7113. Min Range: -4.7113

Max Act: 4.5348. Min Act: -0.1700

Data Index: 5088666 (Open Web Text)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #19