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

Dataset: Open Web Text

Neuron 722 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: 5.1624. Min Range: -5.1624

Max Act: 5.1624. Min Act: -0.1700

Data Index: 3609593 (Open Web Text)

Max Activating Token Index: 564

Text #1

Max Range: 5.1624. Min Range: -5.1624

Max Act: 5.0042. Min Act: -0.1700

Data Index: 7895117 (Open Web Text)

Max Activating Token Index: 143

Text #2

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.9408. Min Act: -0.1700

Data Index: 7519082 (Open Web Text)

Max Activating Token Index: 281

Text #3

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.9246. Min Act: -0.1700

Data Index: 1744098 (Open Web Text)

Max Activating Token Index: 221

Text #4

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.9390. Min Act: -0.1700

Data Index: 6264622 (Open Web Text)

Max Activating Token Index: 241

Text #5

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.8700. Min Act: -0.1700

Data Index: 2338032 (Open Web Text)

Max Activating Token Index: 486

Text #6

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.8228. Min Act: -0.1700

Data Index: 8433490 (Open Web Text)

Max Activating Token Index: 734

Text #7

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.8465. Min Act: -0.1700

Data Index: 8379687 (Open Web Text)

Max Activating Token Index: 130

Text #8

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.7672. Min Act: -0.1700

Data Index: 23539 (Open Web Text)

Max Activating Token Index: 166

Text #9

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.8564. Min Act: -0.1700

Data Index: 2036766 (Open Web Text)

Max Activating Token Index: 462

Text #10

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.8263. Min Act: -0.1700

Data Index: 3340084 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.8196. Min Act: -0.1700

Data Index: 6022248 (Open Web Text)

Max Activating Token Index: 169

Text #12

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.8291. Min Act: -0.1700

Data Index: 6710302 (Open Web Text)

Max Activating Token Index: 342

Text #13

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.8328. Min Act: -0.1700

Data Index: 4815348 (Open Web Text)

Max Activating Token Index: 136

Text #14

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.7870. Min Act: -0.1700

Data Index: 3834173 (Open Web Text)

Max Activating Token Index: 501

Text #15

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.8120. Min Act: -0.1700

Data Index: 1340703 (Open Web Text)

Max Activating Token Index: 410

Text #16

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.7989. Min Act: -0.1700

Data Index: 7954227 (Open Web Text)

Max Activating Token Index: 558

Text #17

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.7907. Min Act: -0.1700

Data Index: 1527252 (Open Web Text)

Max Activating Token Index: 427

Text #18

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.7827. Min Act: -0.1700

Data Index: 5166788 (Open Web Text)

Max Activating Token Index: 164

Text #19

Max Range: 5.1624. Min Range: -5.1624

Max Act: 4.8056. Min Act: -0.1700

Data Index: 1200299 (Open Web Text)

Max Activating Token Index: 624