< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 348 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: 2.2882. Min Range: -2.2882

Max Act: 2.2882. Min Act: -0.1700

Data Index: 4585859 (Open Web Text)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.2475. Min Act: -0.1700

Data Index: 5704246 (Open Web Text)

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.2499. Min Act: -0.1700

Data Index: 1554545 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.2535. Min Act: -0.1700

Data Index: 4946297 (Open Web Text)

Max Activating Token Index: 840

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.2299. Min Act: -0.1700

Data Index: 8384003 (Open Web Text)

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.2072. Min Act: -0.1700

Data Index: 7295784 (Open Web Text)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.2115. Min Act: -0.1700

Data Index: 5470815 (Open Web Text)

Max Activating Token Index: 920

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.2174. Min Act: -0.1699

Data Index: 2780336 (Open Web Text)

Max Activating Token Index: 124

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.1936. Min Act: -0.1700

Data Index: 3992416 (Open Web Text)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.1947. Min Act: -0.1700

Data Index: 3396448 (Open Web Text)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.1908. Min Act: -0.1700

Data Index: 4696868 (Open Web Text)

Max Activating Token Index: 235

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.2032. Min Act: -0.1700

Data Index: 4709132 (Open Web Text)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.2128. Min Act: -0.1700

Data Index: 8742724 (Open Web Text)

Max Activating Token Index: 334

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.1957. Min Act: -0.1700

Data Index: 6127740 (Open Web Text)

Max Activating Token Index: 496

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.1873. Min Act: -0.1700

Data Index: 1791329 (Open Web Text)

Max Activating Token Index: 944

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.1706. Min Act: -0.1700

Data Index: 447583 (Open Web Text)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.1836. Min Act: -0.1700

Data Index: 2016939 (Open Web Text)

Max Activating Token Index: 535

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.1913. Min Act: -0.1700

Data Index: 690487 (Open Web Text)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.1966. Min Act: -0.1700

Data Index: 6706911 (Open Web Text)

Max Activating Token Index: 505

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.2882. Min Range: -2.2882

Max Act: 2.1923. Min Act: -0.1700

Data Index: 6788467 (Open Web Text)

Max Activating Token Index: 840

Click toggle to see full text

Truncated

Full Text #19