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

Dataset: Open Web Text

Neuron 2818 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: 3.6417. Min Range: -3.6417

Max Act: 3.6376. Min Act: -0.1700

Data Index: 6414118 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.6417. Min Act: -0.1700

Data Index: 6253761 (Open Web Text)

Max Activating Token Index: 507

Text #2

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.6076. Min Act: -0.1700

Data Index: 8686262 (Open Web Text)

Max Activating Token Index: 109

Text #3

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.5738. Min Act: -0.1700

Data Index: 7865073 (Open Web Text)

Max Activating Token Index: 282

Text #4

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.5633. Min Act: -0.1700

Data Index: 6156252 (Open Web Text)

Max Activating Token Index: 315

Text #5

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.5671. Min Act: -0.1700

Data Index: 3136394 (Open Web Text)

Max Activating Token Index: 501

Text #6

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.5563. Min Act: -0.1700

Data Index: 6116615 (Open Web Text)

Max Activating Token Index: 318

Text #7

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.5153. Min Act: -0.1700

Data Index: 2005079 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.5032. Min Act: -0.1700

Data Index: 2388703 (Open Web Text)

Max Activating Token Index: 48

Text #9

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.5063. Min Act: -0.1700

Data Index: 5831911 (Open Web Text)

Max Activating Token Index: 278

Text #10

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.5133. Min Act: -0.1700

Data Index: 6215304 (Open Web Text)

Max Activating Token Index: 192

Text #11

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.5309. Min Act: -0.1700

Data Index: 2130324 (Open Web Text)

Max Activating Token Index: 60

Text #12

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.4960. Min Act: -0.1700

Data Index: 7611195 (Open Web Text)

Max Activating Token Index: 952

Text #13

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.5092. Min Act: -0.1700

Data Index: 5608220 (Open Web Text)

Max Activating Token Index: 419

Text #14

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.4828. Min Act: -0.1700

Data Index: 1419767 (Open Web Text)

Max Activating Token Index: 383

Text #15

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.4898. Min Act: -0.1700

Data Index: 4858478 (Open Web Text)

Max Activating Token Index: 592

Text #16

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.4851. Min Act: -0.1700

Data Index: 555037 (Open Web Text)

Max Activating Token Index: 510

Text #17

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.5008. Min Act: -0.1700

Data Index: 4562327 (Open Web Text)

Max Activating Token Index: 771

Text #18

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.4795. Min Act: -0.1700

Data Index: 6566576 (Open Web Text)

Max Activating Token Index: 510

Text #19

Max Range: 3.6417. Min Range: -3.6417

Max Act: 3.4883. Min Act: -0.1700

Data Index: 3308021 (Open Web Text)

Max Activating Token Index: 6