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

Dataset: Open Web Text

Neuron 2752 in Layer 5

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: 5.8917. Min Range: -5.8917

Max Act: 5.8917. Min Act: -0.1700

Data Index: 8445347 (Open Web Text)

Max Activating Token Index: 544

Text #1

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.7872. Min Act: -0.1700

Data Index: 7946407 (Open Web Text)

Max Activating Token Index: 337

Text #2

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.7311. Min Act: -0.1700

Data Index: 5267763 (Open Web Text)

Max Activating Token Index: 567

Text #3

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.7530. Min Act: -0.1700

Data Index: 6197157 (Open Web Text)

Max Activating Token Index: 303

Text #4

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.7158. Min Act: -0.1700

Data Index: 1114118 (Open Web Text)

Max Activating Token Index: 663

Text #5

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.7209. Min Act: -0.1700

Data Index: 5589188 (Open Web Text)

Max Activating Token Index: 735

Text #6

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.6821. Min Act: -0.1700

Data Index: 3871557 (Open Web Text)

Max Activating Token Index: 292

Text #7

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.6560. Min Act: -0.1700

Data Index: 1835543 (Open Web Text)

Max Activating Token Index: 209

Text #8

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.6792. Min Act: -0.1700

Data Index: 4311853 (Open Web Text)

Max Activating Token Index: 334

Text #9

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.6135. Min Act: -0.1700

Data Index: 7316156 (Open Web Text)

Max Activating Token Index: 514

Text #10

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.6248. Min Act: -0.1700

Data Index: 2402389 (Open Web Text)

Max Activating Token Index: 627

Text #11

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.6364. Min Act: -0.1700

Data Index: 2493898 (Open Web Text)

Max Activating Token Index: 665

Text #12

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.6170. Min Act: -0.1700

Data Index: 8524924 (Open Web Text)

Max Activating Token Index: 561

Text #13

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.5850. Min Act: -0.1700

Data Index: 2831729 (Open Web Text)

Max Activating Token Index: 430

Text #14

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.6209. Min Act: -0.1700

Data Index: 7005385 (Open Web Text)

Max Activating Token Index: 375

Text #15

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.5817. Min Act: -0.1700

Data Index: 4570641 (Open Web Text)

Max Activating Token Index: 907

Text #16

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.6005. Min Act: -0.1700

Data Index: 4813376 (Open Web Text)

Max Activating Token Index: 227

Text #17

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.6179. Min Act: -0.1700

Data Index: 7904674 (Open Web Text)

Max Activating Token Index: 224

Text #18

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.5694. Min Act: -0.1700

Data Index: 1584617 (Open Web Text)

Max Activating Token Index: 280

Text #19

Max Range: 5.8917. Min Range: -5.8917

Max Act: 5.5567. Min Act: -0.1700

Data Index: 609413 (Open Web Text)

Max Activating Token Index: 995