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

Dataset: Open Web Text

Neuron 2017 in Layer 6

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: 5.4168. Min Range: -5.4168

Max Act: 5.4022. Min Act: -0.1700

Data Index: 2421287 (Open Web Text)

Max Activating Token Index: 107

Text #1

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.4168. Min Act: -0.1700

Data Index: 1022887 (Open Web Text)

Max Activating Token Index: 160

Text #2

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.3296. Min Act: -0.1700

Data Index: 2167224 (Open Web Text)

Max Activating Token Index: 58

Text #3

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.3222. Min Act: -0.1700

Data Index: 5356379 (Open Web Text)

Max Activating Token Index: 815

Text #4

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.2390. Min Act: -0.1700

Data Index: 8541278 (Open Web Text)

Max Activating Token Index: 886

Text #5

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.2194. Min Act: -0.1700

Data Index: 710477 (Open Web Text)

Max Activating Token Index: 753

Text #6

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.2517. Min Act: -0.1700

Data Index: 7712208 (Open Web Text)

Max Activating Token Index: 874

Text #7

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.2043. Min Act: -0.1700

Data Index: 1848763 (Open Web Text)

Max Activating Token Index: 951

Text #8

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.2108. Min Act: -0.1700

Data Index: 2575070 (Open Web Text)

Max Activating Token Index: 769

Text #9

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.1968. Min Act: -0.1700

Data Index: 5440478 (Open Web Text)

Max Activating Token Index: 534

Text #10

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.1792. Min Act: -0.1700

Data Index: 7148596 (Open Web Text)

Max Activating Token Index: 295

Text #11

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.1806. Min Act: -0.1700

Data Index: 8012529 (Open Web Text)

Max Activating Token Index: 870

Text #12

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.1738. Min Act: -0.1700

Data Index: 6578564 (Open Web Text)

Max Activating Token Index: 461

Text #13

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.1176. Min Act: -0.1700

Data Index: 6464017 (Open Web Text)

Max Activating Token Index: 511

Text #14

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.1660. Min Act: -0.1700

Data Index: 5477267 (Open Web Text)

Max Activating Token Index: 912

Text #15

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.0914. Min Act: -0.1700

Data Index: 1430822 (Open Web Text)

Max Activating Token Index: 557

Text #16

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.1117. Min Act: -0.1700

Data Index: 4570917 (Open Web Text)

Max Activating Token Index: 424

Text #17

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.0608. Min Act: -0.1700

Data Index: 677303 (Open Web Text)

Max Activating Token Index: 679

Text #18

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.0917. Min Act: -0.1700

Data Index: 7699949 (Open Web Text)

Max Activating Token Index: 414

Text #19

Max Range: 5.4168. Min Range: -5.4168

Max Act: 5.1037. Min Act: -0.1700

Data Index: 3761314 (Open Web Text)

Max Activating Token Index: 507