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

Dataset: Open Web Text

Neuron 648 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: 5.1999. Min Range: -5.1999

Max Act: 5.1999. Min Act: -0.1700

Data Index: 8498353 (Open Web Text)

Max Activating Token Index: 651

Text #1

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.1755. Min Act: -0.1700

Data Index: 5212828 (Open Web Text)

Max Activating Token Index: 871

Text #2

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.1741. Min Act: -0.1700

Data Index: 4841826 (Open Web Text)

Max Activating Token Index: 532

Text #3

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.1359. Min Act: -0.1700

Data Index: 3925247 (Open Web Text)

Max Activating Token Index: 112

Text #4

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.1068. Min Act: -0.1700

Data Index: 7186169 (Open Web Text)

Max Activating Token Index: 360

Text #5

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.0798. Min Act: -0.1700

Data Index: 3000880 (Open Web Text)

Max Activating Token Index: 479

Text #6

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.0892. Min Act: -0.1700

Data Index: 823298 (Open Web Text)

Max Activating Token Index: 568

Text #7

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.0783. Min Act: -0.1700

Data Index: 5419726 (Open Web Text)

Max Activating Token Index: 707

Text #8

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.0766. Min Act: -0.1700

Data Index: 3629024 (Open Web Text)

Max Activating Token Index: 336

Text #9

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.0241. Min Act: -0.1700

Data Index: 5233144 (Open Web Text)

Max Activating Token Index: 492

Text #10

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.0337. Min Act: -0.1700

Data Index: 3542686 (Open Web Text)

Max Activating Token Index: 590

Text #11

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.0363. Min Act: -0.1700

Data Index: 5199609 (Open Web Text)

Max Activating Token Index: 675

Text #12

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.0365. Min Act: -0.1700

Data Index: 4957365 (Open Web Text)

Max Activating Token Index: 400

Text #13

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.0386. Min Act: -0.1700

Data Index: 3489195 (Open Web Text)

Max Activating Token Index: 199

Text #14

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.0317. Min Act: -0.1700

Data Index: 7931223 (Open Web Text)

Max Activating Token Index: 365

Text #15

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.0507. Min Act: -0.1700

Data Index: 6599877 (Open Web Text)

Max Activating Token Index: 529

Text #16

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.0555. Min Act: -0.1700

Data Index: 5903643 (Open Web Text)

Max Activating Token Index: 339

Text #17

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.0378. Min Act: -0.1700

Data Index: 5314007 (Open Web Text)

Max Activating Token Index: 717

Text #18

Max Range: 5.1999. Min Range: -5.1999

Max Act: 5.0238. Min Act: -0.1700

Data Index: 2312559 (Open Web Text)

Max Activating Token Index: 844

Text #19

Max Range: 5.1999. Min Range: -5.1999

Max Act: 4.9897. Min Act: -0.1700

Data Index: 2232914 (Open Web Text)

Max Activating Token Index: 211