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

Dataset: Open Web Text

Neuron 2757 in Layer 3

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: 3.9875. Min Range: -3.9875

Max Act: 3.9875. Min Act: -0.1700

Data Index: 5261634 (Open Web Text)

Max Activating Token Index: 781

Text #1

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.9519. Min Act: -0.1700

Data Index: 4905740 (Open Web Text)

Max Activating Token Index: 867

Text #2

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.9552. Min Act: -0.1700

Data Index: 5623529 (Open Web Text)

Max Activating Token Index: 94

Text #3

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.8937. Min Act: -0.1700

Data Index: 7519652 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.8903. Min Act: -0.1700

Data Index: 5199041 (Open Web Text)

Max Activating Token Index: 928

Text #5

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.8545. Min Act: -0.1700

Data Index: 6303309 (Open Web Text)

Max Activating Token Index: 396

Text #6

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.8583. Min Act: -0.1700

Data Index: 8618339 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.8589. Min Act: -0.1700

Data Index: 6282709 (Open Web Text)

Max Activating Token Index: 59

Text #8

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.8520. Min Act: -0.1700

Data Index: 5509544 (Open Web Text)

Max Activating Token Index: 486

Text #9

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.8248. Min Act: -0.1700

Data Index: 6491345 (Open Web Text)

Max Activating Token Index: 161

Text #10

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7896. Min Act: -0.1700

Data Index: 6710404 (Open Web Text)

Max Activating Token Index: 713

Text #11

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.8029. Min Act: -0.1700

Data Index: 4940501 (Open Web Text)

Max Activating Token Index: 990

Text #12

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.8109. Min Act: -0.1700

Data Index: 4231595 (Open Web Text)

Max Activating Token Index: 958

Text #13

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7796. Min Act: -0.1700

Data Index: 4296956 (Open Web Text)

Max Activating Token Index: 633

Text #14

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7754. Min Act: -0.1700

Data Index: 5356830 (Open Web Text)

Max Activating Token Index: 182

Text #15

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7656. Min Act: -0.1700

Data Index: 6150683 (Open Web Text)

Max Activating Token Index: 807

Text #16

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.8045. Min Act: -0.1700

Data Index: 2310689 (Open Web Text)

Max Activating Token Index: 58

Text #17

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7694. Min Act: -0.1700

Data Index: 539642 (Open Web Text)

Max Activating Token Index: 42

Text #18

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7690. Min Act: -0.1700

Data Index: 2724116 (Open Web Text)

Max Activating Token Index: 824

Text #19

Max Range: 3.9875. Min Range: -3.9875

Max Act: 3.7993. Min Act: -0.1700

Data Index: 6224508 (Open Web Text)

Max Activating Token Index: 203