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

Dataset: Open Web Text

Neuron 2882 in Layer 5

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: 4.9984. Min Range: -4.9984

Max Act: 4.9699. Min Act: -0.1700

Data Index: 8167540 (Open Web Text)

Max Activating Token Index: 35

Text #1

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.9984. Min Act: -0.1700

Data Index: 64480 (Open Web Text)

Max Activating Token Index: 165

Text #2

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.9197. Min Act: -0.1700

Data Index: 8566046 (Open Web Text)

Max Activating Token Index: 643

Text #3

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.9736. Min Act: -0.1700

Data Index: 8180390 (Open Web Text)

Max Activating Token Index: 199

Text #4

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.9269. Min Act: -0.1700

Data Index: 6439100 (Open Web Text)

Max Activating Token Index: 814

Text #5

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.9613. Min Act: -0.1700

Data Index: 7413957 (Open Web Text)

Max Activating Token Index: 623

Text #6

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.9308. Min Act: -0.1700

Data Index: 1042729 (Open Web Text)

Max Activating Token Index: 149

Text #7

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.8606. Min Act: -0.1700

Data Index: 7470730 (Open Web Text)

Max Activating Token Index: 343

Text #8

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.8834. Min Act: -0.1700

Data Index: 8241264 (Open Web Text)

Max Activating Token Index: 660

Text #9

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.9134. Min Act: -0.1700

Data Index: 734481 (Open Web Text)

Max Activating Token Index: 659

Text #10

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.8565. Min Act: -0.1700

Data Index: 439631 (Open Web Text)

Max Activating Token Index: 551

Text #11

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.8379. Min Act: -0.1700

Data Index: 4101621 (Open Web Text)

Max Activating Token Index: 976

Text #12

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.8368. Min Act: -0.1700

Data Index: 7857121 (Open Web Text)

Max Activating Token Index: 155

Text #13

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.8221. Min Act: -0.1700

Data Index: 52067 (Open Web Text)

Max Activating Token Index: 480

Text #14

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.8427. Min Act: -0.1700

Data Index: 8277478 (Open Web Text)

Max Activating Token Index: 528

Text #15

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.8554. Min Act: -0.1700

Data Index: 2582611 (Open Web Text)

Max Activating Token Index: 823

Text #16

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.7599. Min Act: -0.1700

Data Index: 6050022 (Open Web Text)

Max Activating Token Index: 567

Text #17

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.8406. Min Act: -0.1700

Data Index: 3595855 (Open Web Text)

Max Activating Token Index: 896

Text #18

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.7542. Min Act: -0.1700

Data Index: 6829448 (Open Web Text)

Max Activating Token Index: 541

Text #19

Max Range: 4.9984. Min Range: -4.9984

Max Act: 4.7639. Min Act: -0.1700

Data Index: 6758225 (Open Web Text)

Max Activating Token Index: 610