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

Dataset: Open Web Text

Neuron 1780 in Layer 0

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: 5.3683. Min Range: -5.3683

Max Act: 5.3683. Min Act: -0.1700

Data Index: 7633496 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.2738. Min Act: -0.1700

Data Index: 3949915 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.2736. Min Act: -0.1700

Data Index: 6296182 (Open Web Text)

Max Activating Token Index: 740

Text #3

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.2377. Min Act: -0.1700

Data Index: 8831559 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.2355. Min Act: -0.1700

Data Index: 677965 (Open Web Text)

Max Activating Token Index: 779

Text #5

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.2179. Min Act: -0.1700

Data Index: 7559390 (Open Web Text)

Max Activating Token Index: 913

Text #6

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.2126. Min Act: -0.1700

Data Index: 7583011 (Open Web Text)

Max Activating Token Index: 593

Text #7

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.1980. Min Act: -0.1700

Data Index: 8534549 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.2225. Min Act: -0.1700

Data Index: 4763080 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.1703. Min Act: -0.1700

Data Index: 8428612 (Open Web Text)

Max Activating Token Index: 664

Text #10

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.1927. Min Act: -0.1700

Data Index: 3882852 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.1860. Min Act: -0.1700

Data Index: 4247979 (Open Web Text)

Max Activating Token Index: 17

Text #12

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.1531. Min Act: -0.1700

Data Index: 207222 (Open Web Text)

Max Activating Token Index: 669

Text #13

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.1355. Min Act: -0.1700

Data Index: 1667078 (Open Web Text)

Max Activating Token Index: 655

Text #14

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.1261. Min Act: -0.1700

Data Index: 1495115 (Open Web Text)

Max Activating Token Index: 993

Text #15

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.1180. Min Act: -0.1700

Data Index: 5417412 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.1207. Min Act: -0.1700

Data Index: 8518409 (Open Web Text)

Max Activating Token Index: 15

Text #17

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.1011. Min Act: -0.1700

Data Index: 7853746 (Open Web Text)

Max Activating Token Index: 862

Text #18

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.1171. Min Act: -0.1700

Data Index: 2178616 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 5.3683. Min Range: -5.3683

Max Act: 5.1137. Min Act: -0.1700

Data Index: 1140062 (Open Web Text)

Max Activating Token Index: 7