< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2615 in Layer 1

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: 2.8289. Min Range: -2.8289

Max Act: 2.8289. Min Act: -0.1700

Data Index: 8373966 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.8130. Min Act: -0.1700

Data Index: 8745813 (Open Web Text)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.7404. Min Act: -0.1700

Data Index: 6142580 (Open Web Text)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.7366. Min Act: -0.1700

Data Index: 2424434 (Open Web Text)

Max Activating Token Index: 280

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.7067. Min Act: -0.1700

Data Index: 1266629 (Open Web Text)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.7091. Min Act: -0.1700

Data Index: 3915742 (Open Web Text)

Max Activating Token Index: 70

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.6949. Min Act: -0.1700

Data Index: 5102911 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.6914. Min Act: -0.1700

Data Index: 5883432 (Open Web Text)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.6995. Min Act: -0.1700

Data Index: 5604550 (Open Web Text)

Max Activating Token Index: 116

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.6724. Min Act: -0.1700

Data Index: 5820774 (Open Web Text)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.6691. Min Act: -0.1700

Data Index: 4218820 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.6815. Min Act: -0.1700

Data Index: 7592018 (Open Web Text)

Max Activating Token Index: 107

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.6634. Min Act: -0.1700

Data Index: 1953463 (Open Web Text)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.6795. Min Act: -0.1700

Data Index: 1129921 (Open Web Text)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.6643. Min Act: -0.1700

Data Index: 744534 (Open Web Text)

Max Activating Token Index: 190

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.6634. Min Act: -0.1700

Data Index: 4077104 (Open Web Text)

Max Activating Token Index: 189

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.6697. Min Act: -0.1700

Data Index: 4554961 (Open Web Text)

Max Activating Token Index: 603

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.6687. Min Act: -0.1700

Data Index: 8398126 (Open Web Text)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.6466. Min Act: -0.1700

Data Index: 856941 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8289. Min Range: -2.8289

Max Act: 2.6561. Min Act: -0.1700

Data Index: 968751 (Open Web Text)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #19