< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2097 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: 2.9376. Min Range: -2.9376

Max Act: 2.9376. Min Act: -0.1700

Data Index: 1488941 (Open Web Text)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8851. Min Act: -0.1700

Data Index: 4259178 (Open Web Text)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8656. Min Act: -0.1700

Data Index: 1925430 (Open Web Text)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8724. Min Act: -0.1700

Data Index: 7640221 (Open Web Text)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8598. Min Act: -0.1700

Data Index: 4860842 (Open Web Text)

Max Activating Token Index: 244

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8655. Min Act: -0.1700

Data Index: 2802772 (Open Web Text)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8591. Min Act: -0.1700

Data Index: 7965733 (Open Web Text)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8424. Min Act: -0.1700

Data Index: 3063820 (Open Web Text)

Max Activating Token Index: 179

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8266. Min Act: -0.1700

Data Index: 562835 (Open Web Text)

Max Activating Token Index: 877

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8093. Min Act: -0.1700

Data Index: 506086 (Open Web Text)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8186. Min Act: -0.1700

Data Index: 1021455 (Open Web Text)

Max Activating Token Index: 776

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8528. Min Act: -0.1700

Data Index: 2512408 (Open Web Text)

Max Activating Token Index: 464

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8087. Min Act: -0.1700

Data Index: 109634 (Open Web Text)

Max Activating Token Index: 324

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8203. Min Act: -0.1700

Data Index: 7802678 (Open Web Text)

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.7847. Min Act: -0.1700

Data Index: 3011438 (Open Web Text)

Max Activating Token Index: 187

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8047. Min Act: -0.1700

Data Index: 7391001 (Open Web Text)

Max Activating Token Index: 640

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8027. Min Act: -0.1700

Data Index: 6136221 (Open Web Text)

Max Activating Token Index: 69

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.7744. Min Act: -0.1700

Data Index: 4516327 (Open Web Text)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.8030. Min Act: -0.1700

Data Index: 3459650 (Open Web Text)

Max Activating Token Index: 106

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9376. Min Range: -2.9376

Max Act: 2.7852. Min Act: -0.1700

Data Index: 2257756 (Open Web Text)

Max Activating Token Index: 226

Click toggle to see full text

Truncated

Full Text #19