< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 567 in Layer 3

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: 2.9171. Min Range: -2.9171

Max Act: 2.8913. Min Act: -0.1700

Data Index: 5308166 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.9171. Min Act: -0.1700

Data Index: 2576960 (Open Web Text)

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.8629. Min Act: -0.1700

Data Index: 3207897 (Open Web Text)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.8336. Min Act: -0.1700

Data Index: 6167190 (Open Web Text)

Max Activating Token Index: 191

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.7739. Min Act: -0.1700

Data Index: 3806159 (Open Web Text)

Max Activating Token Index: 185

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.7726. Min Act: -0.1700

Data Index: 1020064 (Open Web Text)

Max Activating Token Index: 256

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.7561. Min Act: -0.1700

Data Index: 4625902 (Open Web Text)

Max Activating Token Index: 884

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.7489. Min Act: -0.1700

Data Index: 3155282 (Open Web Text)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.7704. Min Act: -0.1700

Data Index: 1887699 (Open Web Text)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.7318. Min Act: -0.1700

Data Index: 288349 (Open Web Text)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.7087. Min Act: -0.1700

Data Index: 5505139 (Open Web Text)

Max Activating Token Index: 883

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.7017. Min Act: -0.1700

Data Index: 5539390 (Open Web Text)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.7023. Min Act: -0.1700

Data Index: 8420131 (Open Web Text)

Max Activating Token Index: 139

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.7025. Min Act: -0.1700

Data Index: 2576961 (Open Web Text)

Max Activating Token Index: 37

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.7094. Min Act: -0.1700

Data Index: 2287680 (Open Web Text)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.6950. Min Act: -0.1700

Data Index: 6605409 (Open Web Text)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.6955. Min Act: -0.1700

Data Index: 2360070 (Open Web Text)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.6970. Min Act: -0.1700

Data Index: 6207564 (Open Web Text)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.6779. Min Act: -0.1700

Data Index: 978087 (Open Web Text)

Max Activating Token Index: 614

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9171. Min Range: -2.9171

Max Act: 2.6903. Min Act: -0.1700

Data Index: 3898380 (Open Web Text)

Max Activating Token Index: 319

Click toggle to see full text

Truncated

Full Text #19