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

Dataset: Open Web Text

Neuron 2014 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: 4.8432. Min Range: -4.8432

Max Act: 4.8432. Min Act: -0.1700

Data Index: 7142370 (Open Web Text)

Max Activating Token Index: 27

Text #1

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.8285. Min Act: -0.1700

Data Index: 1968959 (Open Web Text)

Max Activating Token Index: 337

Text #2

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.8058. Min Act: -0.1700

Data Index: 5522822 (Open Web Text)

Max Activating Token Index: 623

Text #3

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.8263. Min Act: -0.1700

Data Index: 3203623 (Open Web Text)

Max Activating Token Index: 547

Text #4

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.7836. Min Act: -0.1700

Data Index: 2153732 (Open Web Text)

Max Activating Token Index: 56

Text #5

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.7764. Min Act: -0.1700

Data Index: 6884113 (Open Web Text)

Max Activating Token Index: 279

Text #6

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.7521. Min Act: -0.1700

Data Index: 8409848 (Open Web Text)

Max Activating Token Index: 188

Text #7

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.7442. Min Act: -0.1700

Data Index: 8751444 (Open Web Text)

Max Activating Token Index: 851

Text #8

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.7428. Min Act: -0.1700

Data Index: 6863053 (Open Web Text)

Max Activating Token Index: 101

Text #9

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.7611. Min Act: -0.1700

Data Index: 1984896 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.7372. Min Act: -0.1700

Data Index: 6059614 (Open Web Text)

Max Activating Token Index: 284

Text #11

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.7506. Min Act: -0.1700

Data Index: 427310 (Open Web Text)

Max Activating Token Index: 136

Text #12

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.7224. Min Act: -0.1700

Data Index: 4312355 (Open Web Text)

Max Activating Token Index: 265

Text #13

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.6991. Min Act: -0.1700

Data Index: 774059 (Open Web Text)

Max Activating Token Index: 433

Text #14

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.7203. Min Act: -0.1700

Data Index: 6267216 (Open Web Text)

Max Activating Token Index: 873

Text #15

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.7055. Min Act: -0.1700

Data Index: 6023857 (Open Web Text)

Max Activating Token Index: 859

Text #16

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.7284. Min Act: -0.1700

Data Index: 5695919 (Open Web Text)

Max Activating Token Index: 138

Text #17

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.7421. Min Act: -0.1700

Data Index: 1944763 (Open Web Text)

Max Activating Token Index: 400

Text #18

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.7155. Min Act: -0.1700

Data Index: 1849422 (Open Web Text)

Max Activating Token Index: 219

Text #19

Max Range: 4.8432. Min Range: -4.8432

Max Act: 4.7343. Min Act: -0.1700

Data Index: 1768921 (Open Web Text)

Max Activating Token Index: 20