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

Dataset: Open Web Text

Neuron 2691 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: 1.8936. Min Range: -1.8936

Max Act: 1.8936. Min Act: -0.1700

Data Index: 418392 (Open Web Text)

Max Activating Token Index: 460

Text #1

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8842. Min Act: -0.1700

Data Index: 8089566 (Open Web Text)

Max Activating Token Index: 131

Text #2

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8872. Min Act: -0.1700

Data Index: 2796874 (Open Web Text)

Max Activating Token Index: 540

Text #3

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8700. Min Act: -0.1700

Data Index: 4533470 (Open Web Text)

Max Activating Token Index: 562

Text #4

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8747. Min Act: -0.1700

Data Index: 2649473 (Open Web Text)

Max Activating Token Index: 477

Text #5

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8774. Min Act: -0.1700

Data Index: 883599 (Open Web Text)

Max Activating Token Index: 22

Text #6

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8784. Min Act: -0.1700

Data Index: 1458404 (Open Web Text)

Max Activating Token Index: 425

Text #7

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8789. Min Act: -0.1700

Data Index: 3280161 (Open Web Text)

Max Activating Token Index: 329

Text #8

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8739. Min Act: -0.1700

Data Index: 6292089 (Open Web Text)

Max Activating Token Index: 508

Text #9

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8652. Min Act: -0.1700

Data Index: 7350046 (Open Web Text)

Max Activating Token Index: 442

Text #10

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8726. Min Act: -0.1700

Data Index: 1410973 (Open Web Text)

Max Activating Token Index: 45

Text #11

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8621. Min Act: -0.1700

Data Index: 4026777 (Open Web Text)

Max Activating Token Index: 125

Text #12

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8525. Min Act: -0.1700

Data Index: 7247760 (Open Web Text)

Max Activating Token Index: 442

Text #13

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8523. Min Act: -0.1700

Data Index: 7915914 (Open Web Text)

Max Activating Token Index: 651

Text #14

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8627. Min Act: -0.1700

Data Index: 5681036 (Open Web Text)

Max Activating Token Index: 657

Text #15

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8530. Min Act: -0.1700

Data Index: 3896785 (Open Web Text)

Max Activating Token Index: 536

Text #16

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8516. Min Act: -0.1700

Data Index: 3088134 (Open Web Text)

Max Activating Token Index: 496

Text #17

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8435. Min Act: -0.1700

Data Index: 275751 (Open Web Text)

Max Activating Token Index: 600

Text #18

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8525. Min Act: -0.1700

Data Index: 7745011 (Open Web Text)

Max Activating Token Index: 436

Text #19

Max Range: 1.8936. Min Range: -1.8936

Max Act: 1.8377. Min Act: -0.1700

Data Index: 2304990 (Open Web Text)

Max Activating Token Index: 519