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

Dataset: Open Web Text

Neuron 1464 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: 2.0702. Min Range: -2.0702

Max Act: 2.0702. Min Act: -0.1700

Data Index: 1590797 (Open Web Text)

Max Activating Token Index: 206

Text #1

Max Range: 2.0702. Min Range: -2.0702

Max Act: 2.0390. Min Act: -0.1700

Data Index: 1802420 (Open Web Text)

Max Activating Token Index: 203

Text #2

Max Range: 2.0702. Min Range: -2.0702

Max Act: 2.0124. Min Act: -0.1700

Data Index: 7135812 (Open Web Text)

Max Activating Token Index: 657

Text #3

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9961. Min Act: -0.1700

Data Index: 336164 (Open Web Text)

Max Activating Token Index: 703

Text #4

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9773. Min Act: -0.1700

Data Index: 1812701 (Open Web Text)

Max Activating Token Index: 986

Text #5

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9283. Min Act: -0.1700

Data Index: 8396546 (Open Web Text)

Max Activating Token Index: 964

Text #6

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9068. Min Act: -0.1700

Data Index: 1164829 (Open Web Text)

Max Activating Token Index: 605

Text #7

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.9041. Min Act: -0.1700

Data Index: 5455269 (Open Web Text)

Max Activating Token Index: 427

Text #8

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.8858. Min Act: -0.1700

Data Index: 3230505 (Open Web Text)

Max Activating Token Index: 877

Text #9

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.8786. Min Act: -0.1700

Data Index: 3843123 (Open Web Text)

Max Activating Token Index: 991

Text #10

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.8745. Min Act: -0.1700

Data Index: 8258088 (Open Web Text)

Max Activating Token Index: 510

Text #11

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.8672. Min Act: -0.1700

Data Index: 1199941 (Open Web Text)

Max Activating Token Index: 43

Text #12

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.8729. Min Act: -0.1700

Data Index: 1978667 (Open Web Text)

Max Activating Token Index: 947

Text #13

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.8478. Min Act: -0.1700

Data Index: 5029912 (Open Web Text)

Max Activating Token Index: 778

Text #14

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.8414. Min Act: -0.1700

Data Index: 97817 (Open Web Text)

Max Activating Token Index: 624

Text #15

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.8400. Min Act: -0.1700

Data Index: 6399289 (Open Web Text)

Max Activating Token Index: 624

Text #16

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.8386. Min Act: -0.1700

Data Index: 5809264 (Open Web Text)

Max Activating Token Index: 988

Text #17

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.8364. Min Act: -0.1700

Data Index: 6874060 (Open Web Text)

Max Activating Token Index: 324

Text #18

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.8356. Min Act: -0.1700

Data Index: 2915209 (Open Web Text)

Max Activating Token Index: 495

Text #19

Max Range: 2.0702. Min Range: -2.0702

Max Act: 1.8412. Min Act: -0.1700

Data Index: 1916063 (Open Web Text)

Max Activating Token Index: 77