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

Dataset: Open Web Text

Neuron 914 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: 5.1507. Min Range: -5.1507

Max Act: 5.1507. Min Act: -0.1700

Data Index: 3923685 (Open Web Text)

Max Activating Token Index: 110

Text #1

Max Range: 5.1507. Min Range: -5.1507

Max Act: 5.0551. Min Act: -0.1700

Data Index: 864805 (Open Web Text)

Max Activating Token Index: 701

Text #2

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.9879. Min Act: -0.1700

Data Index: 3992500 (Open Web Text)

Max Activating Token Index: 753

Text #3

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.9909. Min Act: -0.1700

Data Index: 1902577 (Open Web Text)

Max Activating Token Index: 475

Text #4

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.9772. Min Act: -0.1700

Data Index: 2684901 (Open Web Text)

Max Activating Token Index: 741

Text #5

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.9464. Min Act: -0.1700

Data Index: 4884114 (Open Web Text)

Max Activating Token Index: 580

Text #6

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.9331. Min Act: -0.1700

Data Index: 4730842 (Open Web Text)

Max Activating Token Index: 113

Text #7

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.9240. Min Act: -0.1700

Data Index: 820516 (Open Web Text)

Max Activating Token Index: 38

Text #8

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.9021. Min Act: -0.1700

Data Index: 8549392 (Open Web Text)

Max Activating Token Index: 815

Text #9

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.9187. Min Act: -0.1700

Data Index: 6842472 (Open Web Text)

Max Activating Token Index: 341

Text #10

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.9449. Min Act: -0.1700

Data Index: 3010201 (Open Web Text)

Max Activating Token Index: 810

Text #11

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.9358. Min Act: -0.1700

Data Index: 3654086 (Open Web Text)

Max Activating Token Index: 215

Text #12

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.8767. Min Act: -0.1700

Data Index: 6208473 (Open Web Text)

Max Activating Token Index: 126

Text #13

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.8815. Min Act: -0.1700

Data Index: 3973214 (Open Web Text)

Max Activating Token Index: 30

Text #14

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.8623. Min Act: -0.1700

Data Index: 3289639 (Open Web Text)

Max Activating Token Index: 802

Text #15

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.8526. Min Act: -0.1700

Data Index: 4576005 (Open Web Text)

Max Activating Token Index: 952

Text #16

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.8247. Min Act: -0.1700

Data Index: 8725970 (Open Web Text)

Max Activating Token Index: 965

Text #17

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.8227. Min Act: -0.1700

Data Index: 2988950 (Open Web Text)

Max Activating Token Index: 438

Text #18

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.8117. Min Act: -0.1700

Data Index: 4377984 (Open Web Text)

Max Activating Token Index: 952

Text #19

Max Range: 5.1507. Min Range: -5.1507

Max Act: 4.7968. Min Act: -0.1700

Data Index: 6765973 (Open Web Text)

Max Activating Token Index: 817