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

Dataset: Open Web Text

Neuron 394 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: 4.3583. Min Range: -4.3583

Max Act: 4.3228. Min Act: -0.1700

Data Index: 762790 (Open Web Text)

Max Activating Token Index: 722

Text #1

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.3583. Min Act: -0.1700

Data Index: 1722904 (Open Web Text)

Max Activating Token Index: 546

Text #2

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.3158. Min Act: -0.1700

Data Index: 1062355 (Open Web Text)

Max Activating Token Index: 317

Text #3

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.2833. Min Act: -0.1700

Data Index: 4671926 (Open Web Text)

Max Activating Token Index: 799

Text #4

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.2672. Min Act: -0.1700

Data Index: 6842743 (Open Web Text)

Max Activating Token Index: 850

Text #5

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.2321. Min Act: -0.1700

Data Index: 4671868 (Open Web Text)

Max Activating Token Index: 608

Text #6

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.1726. Min Act: -0.1700

Data Index: 2020846 (Open Web Text)

Max Activating Token Index: 772

Text #7

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.1704. Min Act: -0.1700

Data Index: 8542347 (Open Web Text)

Max Activating Token Index: 606

Text #8

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.1678. Min Act: -0.1700

Data Index: 2578114 (Open Web Text)

Max Activating Token Index: 478

Text #9

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.1236. Min Act: -0.1700

Data Index: 2491830 (Open Web Text)

Max Activating Token Index: 537

Text #10

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.1043. Min Act: -0.1700

Data Index: 1019775 (Open Web Text)

Max Activating Token Index: 176

Text #11

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.0900. Min Act: -0.1700

Data Index: 8039232 (Open Web Text)

Max Activating Token Index: 731

Text #12

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.0889. Min Act: -0.1700

Data Index: 4915960 (Open Web Text)

Max Activating Token Index: 693

Text #13

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.1095. Min Act: -0.1700

Data Index: 6109472 (Open Web Text)

Max Activating Token Index: 648

Text #14

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.0947. Min Act: -0.1700

Data Index: 5063471 (Open Web Text)

Max Activating Token Index: 48

Text #15

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.0668. Min Act: -0.1700

Data Index: 3245218 (Open Web Text)

Max Activating Token Index: 530

Text #16

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.0704. Min Act: -0.1700

Data Index: 6296539 (Open Web Text)

Max Activating Token Index: 453

Text #17

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.0753. Min Act: -0.1700

Data Index: 1202985 (Open Web Text)

Max Activating Token Index: 512

Text #18

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.0584. Min Act: -0.1700

Data Index: 3928966 (Open Web Text)

Max Activating Token Index: 559

Text #19

Max Range: 4.3583. Min Range: -4.3583

Max Act: 4.0319. Min Act: -0.1700

Data Index: 2292971 (Open Web Text)

Max Activating Token Index: 204