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

Dataset: Open Web Text

Neuron 1024 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: 3.9807. Min Range: -3.9807

Max Act: 3.9807. Min Act: -0.1700

Data Index: 597514 (Open Web Text)

Max Activating Token Index: 560

Text #1

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.9667. Min Act: -0.1700

Data Index: 8224549 (Open Web Text)

Max Activating Token Index: 509

Text #2

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.9461. Min Act: -0.1700

Data Index: 2881778 (Open Web Text)

Max Activating Token Index: 415

Text #3

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.9109. Min Act: -0.1700

Data Index: 1170195 (Open Web Text)

Max Activating Token Index: 196

Text #4

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.9186. Min Act: -0.1700

Data Index: 3209413 (Open Web Text)

Max Activating Token Index: 560

Text #5

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.9162. Min Act: -0.1700

Data Index: 7239145 (Open Web Text)

Max Activating Token Index: 626

Text #6

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.8746. Min Act: -0.1700

Data Index: 7327889 (Open Web Text)

Max Activating Token Index: 471

Text #7

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.8724. Min Act: -0.1700

Data Index: 783936 (Open Web Text)

Max Activating Token Index: 619

Text #8

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.8782. Min Act: -0.1700

Data Index: 5139941 (Open Web Text)

Max Activating Token Index: 607

Text #9

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.8732. Min Act: -0.1700

Data Index: 7254988 (Open Web Text)

Max Activating Token Index: 839

Text #10

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.8753. Min Act: -0.1700

Data Index: 4103979 (Open Web Text)

Max Activating Token Index: 59

Text #11

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.8939. Min Act: -0.1700

Data Index: 1912669 (Open Web Text)

Max Activating Token Index: 62

Text #12

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.9027. Min Act: -0.1700

Data Index: 1906401 (Open Web Text)

Max Activating Token Index: 279

Text #13

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.8836. Min Act: -0.1700

Data Index: 160547 (Open Web Text)

Max Activating Token Index: 386

Text #14

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.8730. Min Act: -0.1700

Data Index: 1828975 (Open Web Text)

Max Activating Token Index: 53

Text #15

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.8788. Min Act: -0.1700

Data Index: 6732818 (Open Web Text)

Max Activating Token Index: 408

Text #16

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.8677. Min Act: -0.1700

Data Index: 6035269 (Open Web Text)

Max Activating Token Index: 139

Text #17

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.8686. Min Act: -0.1700

Data Index: 1454115 (Open Web Text)

Max Activating Token Index: 68

Text #18

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.8830. Min Act: -0.1700

Data Index: 6020882 (Open Web Text)

Max Activating Token Index: 476

Text #19

Max Range: 3.9807. Min Range: -3.9807

Max Act: 3.8913. Min Act: -0.1700

Data Index: 5989204 (Open Web Text)

Max Activating Token Index: 605