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

Dataset: Open Web Text

Neuron 2574 in Layer 5

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: 3.8654. Min Range: -3.8654

Max Act: 3.8654. Min Act: -0.1700

Data Index: 6541653 (Open Web Text)

Max Activating Token Index: 693

Text #1

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.7174. Min Act: -0.1700

Data Index: 1488647 (Open Web Text)

Max Activating Token Index: 334

Text #2

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.7678. Min Act: -0.1700

Data Index: 102886 (Open Web Text)

Max Activating Token Index: 825

Text #3

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.6574. Min Act: -0.1700

Data Index: 3509963 (Open Web Text)

Max Activating Token Index: 586

Text #4

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.5828. Min Act: -0.1700

Data Index: 3592177 (Open Web Text)

Max Activating Token Index: 150

Text #5

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.5752. Min Act: -0.1700

Data Index: 1291326 (Open Web Text)

Max Activating Token Index: 480

Text #6

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.4956. Min Act: -0.1700

Data Index: 6356918 (Open Web Text)

Max Activating Token Index: 442

Text #7

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.4895. Min Act: -0.1700

Data Index: 8699754 (Open Web Text)

Max Activating Token Index: 479

Text #8

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.4503. Min Act: -0.1700

Data Index: 7440693 (Open Web Text)

Max Activating Token Index: 317

Text #9

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.4908. Min Act: -0.1700

Data Index: 3367979 (Open Web Text)

Max Activating Token Index: 783

Text #10

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.4000. Min Act: -0.1700

Data Index: 7625728 (Open Web Text)

Max Activating Token Index: 482

Text #11

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.4501. Min Act: -0.1700

Data Index: 7823725 (Open Web Text)

Max Activating Token Index: 595

Text #12

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.3698. Min Act: -0.1700

Data Index: 6828426 (Open Web Text)

Max Activating Token Index: 786

Text #13

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.3455. Min Act: -0.1700

Data Index: 4966688 (Open Web Text)

Max Activating Token Index: 160

Text #14

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.3920. Min Act: -0.1700

Data Index: 6560177 (Open Web Text)

Max Activating Token Index: 946

Text #15

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.3473. Min Act: -0.1700

Data Index: 1857535 (Open Web Text)

Max Activating Token Index: 78

Text #16

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.3833. Min Act: -0.1700

Data Index: 6672298 (Open Web Text)

Max Activating Token Index: 889

Text #17

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.2632. Min Act: -0.1700

Data Index: 5566126 (Open Web Text)

Max Activating Token Index: 807

Text #18

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.2689. Min Act: -0.1700

Data Index: 3691983 (Open Web Text)

Max Activating Token Index: 327

Text #19

Max Range: 3.8654. Min Range: -3.8654

Max Act: 3.3074. Min Act: -0.1700

Data Index: 5852741 (Open Web Text)

Max Activating Token Index: 277