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

Dataset: Open Web Text

Neuron 2297 in Layer 0

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: 3.1496. Min Range: -3.1496

Max Act: 3.1496. Min Act: -0.1700

Data Index: 6761068 (Open Web Text)

Max Activating Token Index: 8

Text #1

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0216. Min Act: -0.1700

Data Index: 5392150 (Open Web Text)

Max Activating Token Index: 49

Text #2

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0145. Min Act: -0.1700

Data Index: 3436917 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 3.1496. Min Range: -3.1496

Max Act: 3.0028. Min Act: -0.1700

Data Index: 8084804 (Open Web Text)

Max Activating Token Index: 29

Text #4

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.9984. Min Act: -0.1700

Data Index: 8493009 (Open Web Text)

Max Activating Token Index: 15

Text #5

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.9811. Min Act: -0.1700

Data Index: 6329883 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.9817. Min Act: -0.1700

Data Index: 8209793 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.9666. Min Act: -0.1700

Data Index: 1885789 (Open Web Text)

Max Activating Token Index: 37

Text #8

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.9619. Min Act: -0.1700

Data Index: 8483505 (Open Web Text)

Max Activating Token Index: 21

Text #9

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.9482. Min Act: -0.1700

Data Index: 4418280 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.9281. Min Act: -0.1700

Data Index: 398831 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.9425. Min Act: -0.1700

Data Index: 238714 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.9310. Min Act: -0.1700

Data Index: 8473619 (Open Web Text)

Max Activating Token Index: 18

Text #13

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.9255. Min Act: -0.1700

Data Index: 8154051 (Open Web Text)

Max Activating Token Index: 1011

Text #14

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.9184. Min Act: -0.1700

Data Index: 110164 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.9254. Min Act: -0.1700

Data Index: 1059857 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.9315. Min Act: -0.1700

Data Index: 419250 (Open Web Text)

Max Activating Token Index: 600

Text #17

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.9246. Min Act: -0.1700

Data Index: 3509778 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.8989. Min Act: -0.1700

Data Index: 5275473 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 3.1496. Min Range: -3.1496

Max Act: 2.8969. Min Act: -0.1700

Data Index: 3096017 (Open Web Text)

Max Activating Token Index: 44