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

Dataset: Open Web Text

Neuron 2022 in Layer 3

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: 4.8180. Min Range: -4.8180

Max Act: 4.8180. Min Act: -0.1700

Data Index: 1774103 (Open Web Text)

Max Activating Token Index: 591

Text #1

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.7837. Min Act: -0.1700

Data Index: 5278805 (Open Web Text)

Max Activating Token Index: 1002

Text #2

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.7396. Min Act: -0.1700

Data Index: 6932834 (Open Web Text)

Max Activating Token Index: 843

Text #3

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.7324. Min Act: -0.1700

Data Index: 4792467 (Open Web Text)

Max Activating Token Index: 1007

Text #4

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.7552. Min Act: -0.1700

Data Index: 5278806 (Open Web Text)

Max Activating Token Index: 894

Text #5

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.6742. Min Act: -0.1700

Data Index: 1352994 (Open Web Text)

Max Activating Token Index: 862

Text #6

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.6359. Min Act: -0.1700

Data Index: 5410341 (Open Web Text)

Max Activating Token Index: 416

Text #7

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.6172. Min Act: -0.1700

Data Index: 5348549 (Open Web Text)

Max Activating Token Index: 661

Text #8

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.6100. Min Act: -0.1700

Data Index: 215588 (Open Web Text)

Max Activating Token Index: 746

Text #9

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.5843. Min Act: -0.1700

Data Index: 5232685 (Open Web Text)

Max Activating Token Index: 860

Text #10

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.6152. Min Act: -0.1700

Data Index: 1018507 (Open Web Text)

Max Activating Token Index: 978

Text #11

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.5864. Min Act: -0.1700

Data Index: 1018500 (Open Web Text)

Max Activating Token Index: 978

Text #12

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.6003. Min Act: -0.1700

Data Index: 5278807 (Open Web Text)

Max Activating Token Index: 780

Text #13

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.5771. Min Act: -0.1700

Data Index: 8721607 (Open Web Text)

Max Activating Token Index: 430

Text #14

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.5948. Min Act: -0.1700

Data Index: 1018508 (Open Web Text)

Max Activating Token Index: 984

Text #15

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.5376. Min Act: -0.1700

Data Index: 1018503 (Open Web Text)

Max Activating Token Index: 716

Text #16

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.5767. Min Act: -0.1700

Data Index: 1598684 (Open Web Text)

Max Activating Token Index: 602

Text #17

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.5656. Min Act: -0.1700

Data Index: 505214 (Open Web Text)

Max Activating Token Index: 685

Text #18

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.5700. Min Act: -0.1700

Data Index: 1018501 (Open Web Text)

Max Activating Token Index: 664

Text #19

Max Range: 4.8180. Min Range: -4.8180

Max Act: 4.5629. Min Act: -0.1700

Data Index: 1018506 (Open Web Text)

Max Activating Token Index: 962