< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 214 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: 1.6836. Min Range: -1.6836

Max Act: 1.6836. Min Act: -0.1700

Data Index: 7344616 (Open Web Text)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.6555. Min Act: -0.1700

Data Index: 5002704 (Open Web Text)

Max Activating Token Index: 260

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.6448. Min Act: -0.1700

Data Index: 297676 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.6504. Min Act: -0.1700

Data Index: 3594099 (Open Web Text)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.6508. Min Act: -0.1700

Data Index: 1260006 (Open Web Text)

Max Activating Token Index: 882

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.6233. Min Act: -0.1700

Data Index: 1648750 (Open Web Text)

Max Activating Token Index: 478

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.6208. Min Act: -0.1700

Data Index: 3984739 (Open Web Text)

Max Activating Token Index: 590

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.6279. Min Act: -0.1700

Data Index: 8301825 (Open Web Text)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.6088. Min Act: -0.1700

Data Index: 8786591 (Open Web Text)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.6306. Min Act: -0.1700

Data Index: 5027591 (Open Web Text)

Max Activating Token Index: 423

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.6116. Min Act: -0.1700

Data Index: 1403960 (Open Web Text)

Max Activating Token Index: 417

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.6030. Min Act: -0.1700

Data Index: 2697764 (Open Web Text)

Max Activating Token Index: 286

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.6031. Min Act: -0.1700

Data Index: 186432 (Open Web Text)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.5926. Min Act: -0.1699

Data Index: 2445760 (Open Web Text)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.5983. Min Act: -0.1700

Data Index: 5145624 (Open Web Text)

Max Activating Token Index: 445

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.5518. Min Act: -0.1700

Data Index: 7191494 (Open Web Text)

Max Activating Token Index: 810

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.5834. Min Act: -0.1700

Data Index: 6510371 (Open Web Text)

Max Activating Token Index: 28

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.5881. Min Act: -0.1700

Data Index: 3424209 (Open Web Text)

Max Activating Token Index: 149

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.5476. Min Act: -0.1696

Data Index: 6388754 (Open Web Text)

Max Activating Token Index: 996

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 1.6836. Min Range: -1.6836

Max Act: 1.5773. Min Act: -0.1700

Data Index: 6041947 (Open Web Text)

Max Activating Token Index: 106

Click toggle to see full text

Truncated

Full Text #19