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

Dataset: Open Web Text

Neuron 1957 in Layer 2

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: 4.6609. Min Range: -4.6609

Max Act: 4.6609. Min Act: -0.1700

Data Index: 1698177 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.4505. Min Act: -0.1700

Data Index: 6999500 (Open Web Text)

Max Activating Token Index: 874

Text #2

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.4583. Min Act: -0.1700

Data Index: 6825115 (Open Web Text)

Max Activating Token Index: 143

Text #3

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.4523. Min Act: -0.1700

Data Index: 63623 (Open Web Text)

Max Activating Token Index: 440

Text #4

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.4384. Min Act: -0.1700

Data Index: 3391977 (Open Web Text)

Max Activating Token Index: 487

Text #5

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.4235. Min Act: -0.1700

Data Index: 1230767 (Open Web Text)

Max Activating Token Index: 870

Text #6

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.4602. Min Act: -0.1700

Data Index: 4502077 (Open Web Text)

Max Activating Token Index: 579

Text #7

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.4387. Min Act: -0.1700

Data Index: 526827 (Open Web Text)

Max Activating Token Index: 843

Text #8

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.4166. Min Act: -0.1700

Data Index: 5950772 (Open Web Text)

Max Activating Token Index: 94

Text #9

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.3970. Min Act: -0.1700

Data Index: 7760848 (Open Web Text)

Max Activating Token Index: 174

Text #10

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.4039. Min Act: -0.1700

Data Index: 7082698 (Open Web Text)

Max Activating Token Index: 891

Text #11

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.4135. Min Act: -0.1700

Data Index: 2614066 (Open Web Text)

Max Activating Token Index: 273

Text #12

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.3939. Min Act: -0.1700

Data Index: 6911600 (Open Web Text)

Max Activating Token Index: 317

Text #13

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.3918. Min Act: -0.1700

Data Index: 6748875 (Open Web Text)

Max Activating Token Index: 775

Text #14

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.4089. Min Act: -0.1700

Data Index: 5291765 (Open Web Text)

Max Activating Token Index: 610

Text #15

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.4135. Min Act: -0.1700

Data Index: 649648 (Open Web Text)

Max Activating Token Index: 428

Text #16

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.3906. Min Act: -0.1700

Data Index: 1837755 (Open Web Text)

Max Activating Token Index: 692

Text #17

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.4429. Min Act: -0.1700

Data Index: 4548285 (Open Web Text)

Max Activating Token Index: 580

Text #18

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.4131. Min Act: -0.1700

Data Index: 4317700 (Open Web Text)

Max Activating Token Index: 36

Text #19

Max Range: 4.6609. Min Range: -4.6609

Max Act: 4.4057. Min Act: -0.1700

Data Index: 3705067 (Open Web Text)

Max Activating Token Index: 413