< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 929 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')

Text #0

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.8784. Min Act: -0.1700

Data Index: 1226799 (Open Web Text)

Max Activating Token Index: 461

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.8750. Min Act: -0.1700

Data Index: 6707747 (Open Web Text)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.8352. Min Act: -0.1700

Data Index: 5190897 (Open Web Text)

Max Activating Token Index: 270

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.7821. Min Act: -0.1700

Data Index: 4007137 (Open Web Text)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.7801. Min Act: -0.1700

Data Index: 1321897 (Open Web Text)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.7586. Min Act: -0.1700

Data Index: 8173489 (Open Web Text)

Max Activating Token Index: 517

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.7408. Min Act: -0.1700

Data Index: 8626152 (Open Web Text)

Max Activating Token Index: 216

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.7104. Min Act: -0.1700

Data Index: 665090 (Open Web Text)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.7027. Min Act: -0.1700

Data Index: 7291270 (Open Web Text)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.7153. Min Act: -0.1700

Data Index: 7972401 (Open Web Text)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.7048. Min Act: -0.1700

Data Index: 3390467 (Open Web Text)

Max Activating Token Index: 299

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.7138. Min Act: -0.1700

Data Index: 6839493 (Open Web Text)

Max Activating Token Index: 490

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.6867. Min Act: -0.1700

Data Index: 4078441 (Open Web Text)

Max Activating Token Index: 647

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.6864. Min Act: -0.1700

Data Index: 2829375 (Open Web Text)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.6867. Min Act: -0.1700

Data Index: 2466137 (Open Web Text)

Max Activating Token Index: 247

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.6891. Min Act: -0.1700

Data Index: 7030357 (Open Web Text)

Max Activating Token Index: 645

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.6647. Min Act: -0.1700

Data Index: 4255574 (Open Web Text)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.6334. Min Act: -0.1700

Data Index: 7912877 (Open Web Text)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.6350. Min Act: -0.1700

Data Index: 1503077 (Open Web Text)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.8784. Min Range: -2.8784

Max Act: 2.6594. Min Act: -0.1700

Data Index: 7960787 (Open Web Text)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #19