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

Dataset: Open Web Text

Neuron 577 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: 5.1875. Min Range: -5.1875

Max Act: 5.1875. Min Act: -0.1700

Data Index: 1055504 (Open Web Text)

Max Activating Token Index: 309

Text #1

Max Range: 5.1875. Min Range: -5.1875

Max Act: 5.1677. Min Act: -0.1698

Data Index: 5511276 (Open Web Text)

Max Activating Token Index: 589

Text #2

Max Range: 5.1875. Min Range: -5.1875

Max Act: 5.1809. Min Act: -0.1700

Data Index: 677451 (Open Web Text)

Max Activating Token Index: 95

Text #3

Max Range: 5.1875. Min Range: -5.1875

Max Act: 5.1246. Min Act: -0.1700

Data Index: 6050143 (Open Web Text)

Max Activating Token Index: 920

Text #4

Max Range: 5.1875. Min Range: -5.1875

Max Act: 5.1316. Min Act: -0.1700

Data Index: 1004294 (Open Web Text)

Max Activating Token Index: 119

Text #5

Max Range: 5.1875. Min Range: -5.1875

Max Act: 5.1320. Min Act: -0.1700

Data Index: 4760670 (Open Web Text)

Max Activating Token Index: 74

Text #6

Max Range: 5.1875. Min Range: -5.1875

Max Act: 5.0621. Min Act: -0.1700

Data Index: 3927252 (Open Web Text)

Max Activating Token Index: 42

Text #7

Max Range: 5.1875. Min Range: -5.1875

Max Act: 5.0932. Min Act: -0.1700

Data Index: 4146693 (Open Web Text)

Max Activating Token Index: 74

Text #8

Max Range: 5.1875. Min Range: -5.1875

Max Act: 5.0497. Min Act: -0.1697

Data Index: 6207372 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 5.1875. Min Range: -5.1875

Max Act: 5.0306. Min Act: -0.1700

Data Index: 4071427 (Open Web Text)

Max Activating Token Index: 106

Text #10

Max Range: 5.1875. Min Range: -5.1875

Max Act: 5.0430. Min Act: -0.1700

Data Index: 713410 (Open Web Text)

Max Activating Token Index: 79

Text #11

Max Range: 5.1875. Min Range: -5.1875

Max Act: 5.0497. Min Act: -0.1699

Data Index: 1305088 (Open Web Text)

Max Activating Token Index: 38

Text #12

Max Range: 5.1875. Min Range: -5.1875

Max Act: 5.0205. Min Act: -0.1700

Data Index: 793191 (Open Web Text)

Max Activating Token Index: 502

Text #13

Max Range: 5.1875. Min Range: -5.1875

Max Act: 4.9696. Min Act: -0.1695

Data Index: 2833312 (Open Web Text)

Max Activating Token Index: 998

Text #14

Max Range: 5.1875. Min Range: -5.1875

Max Act: 5.0000. Min Act: -0.1700

Data Index: 8287982 (Open Web Text)

Max Activating Token Index: 60

Text #15

Max Range: 5.1875. Min Range: -5.1875

Max Act: 4.9873. Min Act: -0.1700

Data Index: 3736306 (Open Web Text)

Max Activating Token Index: 438

Text #16

Max Range: 5.1875. Min Range: -5.1875

Max Act: 4.9912. Min Act: -0.1700

Data Index: 5781942 (Open Web Text)

Max Activating Token Index: 890

Text #17

Max Range: 5.1875. Min Range: -5.1875

Max Act: 4.9729. Min Act: -0.1700

Data Index: 2542923 (Open Web Text)

Max Activating Token Index: 384

Text #18

Max Range: 5.1875. Min Range: -5.1875

Max Act: 4.9490. Min Act: -0.1700

Data Index: 3639594 (Open Web Text)

Max Activating Token Index: 223

Text #19

Max Range: 5.1875. Min Range: -5.1875

Max Act: 4.9876. Min Act: -0.1700

Data Index: 7658620 (Open Web Text)

Max Activating Token Index: 622