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

Dataset: Open Web Text

Neuron 2248 in Layer 6

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: 3.0262. Min Range: -3.0262

Max Act: 3.0221. Min Act: -0.1700

Data Index: 6166557 (Open Web Text)

Max Activating Token Index: 851

Text #1

Max Range: 3.0262. Min Range: -3.0262

Max Act: 3.0262. Min Act: -0.1700

Data Index: 7656349 (Open Web Text)

Max Activating Token Index: 137

Text #2

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.9634. Min Act: -0.1700

Data Index: 3677094 (Open Web Text)

Max Activating Token Index: 1005

Text #3

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.8572. Min Act: -0.1700

Data Index: 1518703 (Open Web Text)

Max Activating Token Index: 607

Text #4

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.8538. Min Act: -0.1700

Data Index: 6232019 (Open Web Text)

Max Activating Token Index: 635

Text #5

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.8388. Min Act: -0.1700

Data Index: 6166558 (Open Web Text)

Max Activating Token Index: 1003

Text #6

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.8384. Min Act: -0.1700

Data Index: 87252 (Open Web Text)

Max Activating Token Index: 949

Text #7

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.8409. Min Act: -0.1700

Data Index: 3099855 (Open Web Text)

Max Activating Token Index: 555

Text #8

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.8224. Min Act: -0.1700

Data Index: 159979 (Open Web Text)

Max Activating Token Index: 368

Text #9

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.8250. Min Act: -0.1700

Data Index: 918302 (Open Web Text)

Max Activating Token Index: 795

Text #10

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.8040. Min Act: -0.1700

Data Index: 7453429 (Open Web Text)

Max Activating Token Index: 916

Text #11

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.8073. Min Act: -0.1700

Data Index: 5472833 (Open Web Text)

Max Activating Token Index: 890

Text #12

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.8166. Min Act: -0.1700

Data Index: 673589 (Open Web Text)

Max Activating Token Index: 673

Text #13

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.8279. Min Act: -0.1700

Data Index: 3490066 (Open Web Text)

Max Activating Token Index: 1000

Text #14

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.8133. Min Act: -0.1700

Data Index: 4144092 (Open Web Text)

Max Activating Token Index: 664

Text #15

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.8025. Min Act: -0.1700

Data Index: 7560529 (Open Web Text)

Max Activating Token Index: 551

Text #16

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.7838. Min Act: -0.1700

Data Index: 8310126 (Open Web Text)

Max Activating Token Index: 418

Text #17

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.8000. Min Act: -0.1700

Data Index: 5677294 (Open Web Text)

Max Activating Token Index: 992

Text #18

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.8050. Min Act: -0.1700

Data Index: 6166556 (Open Web Text)

Max Activating Token Index: 562

Text #19

Max Range: 3.0262. Min Range: -3.0262

Max Act: 2.7936. Min Act: -0.1700

Data Index: 730817 (Open Web Text)

Max Activating Token Index: 912