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

Dataset: Open Web Text

Neuron 642 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: 3.1722. Min Range: -3.1722

Max Act: 3.1200. Min Act: -0.1700

Data Index: 7946680 (Open Web Text)

Max Activating Token Index: 204

Text #1

Max Range: 3.1722. Min Range: -3.1722

Max Act: 3.1722. Min Act: -0.1700

Data Index: 4698995 (Open Web Text)

Max Activating Token Index: 870

Text #2

Max Range: 3.1722. Min Range: -3.1722

Max Act: 3.0594. Min Act: -0.1700

Data Index: 3769862 (Open Web Text)

Max Activating Token Index: 424

Text #3

Max Range: 3.1722. Min Range: -3.1722

Max Act: 3.0497. Min Act: -0.1700

Data Index: 1460156 (Open Web Text)

Max Activating Token Index: 669

Text #4

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.9782. Min Act: -0.1700

Data Index: 2291570 (Open Web Text)

Max Activating Token Index: 444

Text #5

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.9718. Min Act: -0.1700

Data Index: 1031086 (Open Web Text)

Max Activating Token Index: 123

Text #6

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.9400. Min Act: -0.1700

Data Index: 8220525 (Open Web Text)

Max Activating Token Index: 715

Text #7

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.9543. Min Act: -0.1700

Data Index: 3189186 (Open Web Text)

Max Activating Token Index: 728

Text #8

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.9155. Min Act: -0.1700

Data Index: 4844964 (Open Web Text)

Max Activating Token Index: 68

Text #9

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.8752. Min Act: -0.1700

Data Index: 4258139 (Open Web Text)

Max Activating Token Index: 221

Text #10

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.8584. Min Act: -0.1700

Data Index: 8810479 (Open Web Text)

Max Activating Token Index: 815

Text #11

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.7904. Min Act: -0.1700

Data Index: 2881941 (Open Web Text)

Max Activating Token Index: 910

Text #12

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.8571. Min Act: -0.1700

Data Index: 4243681 (Open Web Text)

Max Activating Token Index: 988

Text #13

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.8540. Min Act: -0.1700

Data Index: 3005369 (Open Web Text)

Max Activating Token Index: 665

Text #14

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.9107. Min Act: -0.1700

Data Index: 1819108 (Open Web Text)

Max Activating Token Index: 627

Text #15

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.8322. Min Act: -0.1700

Data Index: 6257183 (Open Web Text)

Max Activating Token Index: 803

Text #16

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.7832. Min Act: -0.1700

Data Index: 4540916 (Open Web Text)

Max Activating Token Index: 745

Text #17

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.8616. Min Act: -0.1700

Data Index: 1966887 (Open Web Text)

Max Activating Token Index: 151

Text #18

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.8339. Min Act: -0.1700

Data Index: 8052657 (Open Web Text)

Max Activating Token Index: 906

Text #19

Max Range: 3.1722. Min Range: -3.1722

Max Act: 2.8364. Min Act: -0.1700

Data Index: 4774603 (Open Web Text)

Max Activating Token Index: 677