< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 893 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: 2.0446. Min Range: -2.0446

Max Act: 2.0446. Min Act: -0.1700

Data Index: 8359389 (Open Web Text)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.0446. Min Range: -2.0446

Max Act: 2.0314. Min Act: -0.1700

Data Index: 3449894 (Open Web Text)

Max Activating Token Index: 104

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.0446. Min Range: -2.0446

Max Act: 2.0101. Min Act: -0.1700

Data Index: 8044058 (Open Web Text)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.0446. Min Range: -2.0446

Max Act: 2.0081. Min Act: -0.1700

Data Index: 5397101 (Open Web Text)

Max Activating Token Index: 756

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.9992. Min Act: -0.1700

Data Index: 1175796 (Open Web Text)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.9989. Min Act: -0.1700

Data Index: 6675132 (Open Web Text)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.9669. Min Act: -0.1700

Data Index: 7804306 (Open Web Text)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.9616. Min Act: -0.1700

Data Index: 4765926 (Open Web Text)

Max Activating Token Index: 787

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.9282. Min Act: -0.1700

Data Index: 4976887 (Open Web Text)

Max Activating Token Index: 708

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.9102. Min Act: -0.1700

Data Index: 2603767 (Open Web Text)

Max Activating Token Index: 985

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.8996. Min Act: -0.1700

Data Index: 1211486 (Open Web Text)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.8859. Min Act: -0.1700

Data Index: 1900193 (Open Web Text)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.8950. Min Act: -0.1700

Data Index: 1165372 (Open Web Text)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.8818. Min Act: -0.1700

Data Index: 583511 (Open Web Text)

Max Activating Token Index: 61

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.8955. Min Act: -0.1700

Data Index: 7630859 (Open Web Text)

Max Activating Token Index: 813

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.9007. Min Act: -0.1700

Data Index: 1609247 (Open Web Text)

Max Activating Token Index: 394

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.8934. Min Act: -0.1700

Data Index: 7598755 (Open Web Text)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.8980. Min Act: -0.1700

Data Index: 7335666 (Open Web Text)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.9108. Min Act: -0.1700

Data Index: 2873242 (Open Web Text)

Max Activating Token Index: 928

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.0446. Min Range: -2.0446

Max Act: 1.8847. Min Act: -0.1700

Data Index: 2165538 (Open Web Text)

Max Activating Token Index: 825

Click toggle to see full text

Truncated

Full Text #19