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

Dataset: Open Web Text

Neuron 1768 in Layer 4

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: 3.0580. Min Range: -3.0580

Max Act: 3.0580. Min Act: -0.1700

Data Index: 1599880 (Open Web Text)

Max Activating Token Index: 472

Text #1

Max Range: 3.0580. Min Range: -3.0580

Max Act: 3.0193. Min Act: -0.1700

Data Index: 6569088 (Open Web Text)

Max Activating Token Index: 606

Text #2

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9873. Min Act: -0.1700

Data Index: 2779849 (Open Web Text)

Max Activating Token Index: 998

Text #3

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9836. Min Act: -0.1700

Data Index: 5838256 (Open Web Text)

Max Activating Token Index: 567

Text #4

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9882. Min Act: -0.1700

Data Index: 395556 (Open Web Text)

Max Activating Token Index: 384

Text #5

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9469. Min Act: -0.1700

Data Index: 2485370 (Open Web Text)

Max Activating Token Index: 638

Text #6

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9334. Min Act: -0.1700

Data Index: 8387165 (Open Web Text)

Max Activating Token Index: 243

Text #7

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9708. Min Act: -0.1700

Data Index: 6141232 (Open Web Text)

Max Activating Token Index: 627

Text #8

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9882. Min Act: -0.1700

Data Index: 2779844 (Open Web Text)

Max Activating Token Index: 353

Text #9

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9514. Min Act: -0.1700

Data Index: 1511142 (Open Web Text)

Max Activating Token Index: 106

Text #10

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9518. Min Act: -0.1700

Data Index: 2250622 (Open Web Text)

Max Activating Token Index: 778

Text #11

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9480. Min Act: -0.1700

Data Index: 855607 (Open Web Text)

Max Activating Token Index: 976

Text #12

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9275. Min Act: -0.1700

Data Index: 6914387 (Open Web Text)

Max Activating Token Index: 109

Text #13

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9332. Min Act: -0.1700

Data Index: 8064587 (Open Web Text)

Max Activating Token Index: 288

Text #14

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9204. Min Act: -0.1700

Data Index: 3367236 (Open Web Text)

Max Activating Token Index: 534

Text #15

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8920. Min Act: -0.1700

Data Index: 2250624 (Open Web Text)

Max Activating Token Index: 540

Text #16

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9277. Min Act: -0.1700

Data Index: 3035351 (Open Web Text)

Max Activating Token Index: 678

Text #17

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.9269. Min Act: -0.1700

Data Index: 6859701 (Open Web Text)

Max Activating Token Index: 868

Text #18

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8849. Min Act: -0.1700

Data Index: 872756 (Open Web Text)

Max Activating Token Index: 937

Text #19

Max Range: 3.0580. Min Range: -3.0580

Max Act: 2.8895. Min Act: -0.1700

Data Index: 6476760 (Open Web Text)

Max Activating Token Index: 550