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

Dataset: Open Web Text

Neuron 2717 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: 2.0205. Min Range: -2.0205

Max Act: 2.0205. Min Act: -0.1700

Data Index: 1720977 (Open Web Text)

Max Activating Token Index: 602

Text #1

Max Range: 2.0205. Min Range: -2.0205

Max Act: 2.0043. Min Act: -0.1700

Data Index: 7486364 (Open Web Text)

Max Activating Token Index: 753

Text #2

Max Range: 2.0205. Min Range: -2.0205

Max Act: 2.0091. Min Act: -0.1700

Data Index: 6959286 (Open Web Text)

Max Activating Token Index: 694

Text #3

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.9624. Min Act: -0.1700

Data Index: 8099197 (Open Web Text)

Max Activating Token Index: 702

Text #4

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.9831. Min Act: -0.1700

Data Index: 8604992 (Open Web Text)

Max Activating Token Index: 598

Text #5

Max Range: 2.0205. Min Range: -2.0205

Max Act: 2.0024. Min Act: -0.1700

Data Index: 3149744 (Open Web Text)

Max Activating Token Index: 1023

Text #6

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.9415. Min Act: -0.1700

Data Index: 4674160 (Open Web Text)

Max Activating Token Index: 845

Text #7

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.9422. Min Act: -0.1700

Data Index: 5827157 (Open Web Text)

Max Activating Token Index: 656

Text #8

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.9131. Min Act: -0.1700

Data Index: 2825454 (Open Web Text)

Max Activating Token Index: 477

Text #9

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.9211. Min Act: -0.1700

Data Index: 208977 (Open Web Text)

Max Activating Token Index: 807

Text #10

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.9291. Min Act: -0.1700

Data Index: 7474353 (Open Web Text)

Max Activating Token Index: 672

Text #11

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.9045. Min Act: -0.1700

Data Index: 8314409 (Open Web Text)

Max Activating Token Index: 440

Text #12

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.8995. Min Act: -0.1700

Data Index: 2259298 (Open Web Text)

Max Activating Token Index: 499

Text #13

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.8765. Min Act: -0.1700

Data Index: 8530404 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.8964. Min Act: -0.1700

Data Index: 6583522 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.8793. Min Act: -0.1700

Data Index: 5887315 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.8793. Min Act: -0.1700

Data Index: 7098058 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.8861. Min Act: -0.1700

Data Index: 4471327 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.8753. Min Act: -0.1700

Data Index: 7225733 (Open Web Text)

Max Activating Token Index: 795

Text #19

Max Range: 2.0205. Min Range: -2.0205

Max Act: 1.8676. Min Act: -0.1700

Data Index: 4796642 (Open Web Text)

Max Activating Token Index: 363