< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2492 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: 2.9841. Min Range: -2.9841

Max Act: 2.9841. Min Act: -0.1700

Data Index: 5110139 (Open Web Text)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.9196. Min Act: -0.1700

Data Index: 6051541 (Open Web Text)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.9224. Min Act: -0.1700

Data Index: 7257044 (Open Web Text)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.9080. Min Act: -0.1700

Data Index: 3100481 (Open Web Text)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8888. Min Act: -0.1700

Data Index: 7621308 (Open Web Text)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8893. Min Act: -0.1700

Data Index: 1046726 (Open Web Text)

Max Activating Token Index: 143

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8829. Min Act: -0.1700

Data Index: 530694 (Open Web Text)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8589. Min Act: -0.1700

Data Index: 7274010 (Open Web Text)

Max Activating Token Index: 951

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8633. Min Act: -0.1700

Data Index: 8012331 (Open Web Text)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8521. Min Act: -0.1700

Data Index: 7610053 (Open Web Text)

Max Activating Token Index: 41

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8703. Min Act: -0.1700

Data Index: 7308970 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8489. Min Act: -0.1700

Data Index: 7128457 (Open Web Text)

Max Activating Token Index: 453

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8592. Min Act: -0.1700

Data Index: 8115913 (Open Web Text)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8239. Min Act: -0.1700

Data Index: 192851 (Open Web Text)

Max Activating Token Index: 1012

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8260. Min Act: -0.1700

Data Index: 6877067 (Open Web Text)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8272. Min Act: -0.1700

Data Index: 5557574 (Open Web Text)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8111. Min Act: -0.1700

Data Index: 3783152 (Open Web Text)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8169. Min Act: -0.1700

Data Index: 7438960 (Open Web Text)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8166. Min Act: -0.1700

Data Index: 4768673 (Open Web Text)

Max Activating Token Index: 95

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9841. Min Range: -2.9841

Max Act: 2.8025. Min Act: -0.1700

Data Index: 7637641 (Open Web Text)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #19