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

Dataset: Open Web Text

Neuron 1379 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: 1.8338. Min Range: -1.8338

Max Act: 1.8338. Min Act: -0.1700

Data Index: 1498182 (Open Web Text)

Max Activating Token Index: 203

Text #1

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6906. Min Act: -0.1700

Data Index: 4945664 (Open Web Text)

Max Activating Token Index: 134

Text #2

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6899. Min Act: -0.1700

Data Index: 5036767 (Open Web Text)

Max Activating Token Index: 36

Text #3

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6826. Min Act: -0.1700

Data Index: 8213675 (Open Web Text)

Max Activating Token Index: 599

Text #4

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6798. Min Act: -0.1700

Data Index: 166539 (Open Web Text)

Max Activating Token Index: 901

Text #5

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6840. Min Act: -0.1700

Data Index: 967146 (Open Web Text)

Max Activating Token Index: 90

Text #6

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6762. Min Act: -0.1700

Data Index: 4868110 (Open Web Text)

Max Activating Token Index: 519

Text #7

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6808. Min Act: -0.1700

Data Index: 7914984 (Open Web Text)

Max Activating Token Index: 140

Text #8

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6775. Min Act: -0.1700

Data Index: 2884096 (Open Web Text)

Max Activating Token Index: 573

Text #9

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6640. Min Act: -0.1700

Data Index: 5918679 (Open Web Text)

Max Activating Token Index: 417

Text #10

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6678. Min Act: -0.1700

Data Index: 2208593 (Open Web Text)

Max Activating Token Index: 655

Text #11

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6711. Min Act: -0.1700

Data Index: 2167638 (Open Web Text)

Max Activating Token Index: 590

Text #12

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6682. Min Act: -0.1700

Data Index: 3692150 (Open Web Text)

Max Activating Token Index: 246

Text #13

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6584. Min Act: -0.1700

Data Index: 7738323 (Open Web Text)

Max Activating Token Index: 41

Text #14

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6651. Min Act: -0.1700

Data Index: 4050225 (Open Web Text)

Max Activating Token Index: 648

Text #15

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6538. Min Act: -0.1700

Data Index: 3071791 (Open Web Text)

Max Activating Token Index: 447

Text #16

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6564. Min Act: -0.1700

Data Index: 7294019 (Open Web Text)

Max Activating Token Index: 86

Text #17

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6561. Min Act: -0.1700

Data Index: 291287 (Open Web Text)

Max Activating Token Index: 410

Text #18

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6682. Min Act: -0.1700

Data Index: 3830606 (Open Web Text)

Max Activating Token Index: 1004

Text #19

Max Range: 1.8338. Min Range: -1.8338

Max Act: 1.6562. Min Act: -0.1700

Data Index: 2257712 (Open Web Text)

Max Activating Token Index: 216