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

Dataset: Open Web Text

Neuron 2300 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: 3.7896. Min Range: -3.7896

Max Act: 3.7896. Min Act: -0.1700

Data Index: 3422905 (Open Web Text)

Max Activating Token Index: 112

Text #1

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.7035. Min Act: -0.1700

Data Index: 1410552 (Open Web Text)

Max Activating Token Index: 30

Text #2

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.6817. Min Act: -0.1700

Data Index: 7939267 (Open Web Text)

Max Activating Token Index: 700

Text #3

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.6744. Min Act: -0.1700

Data Index: 304556 (Open Web Text)

Max Activating Token Index: 824

Text #4

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.6723. Min Act: -0.1700

Data Index: 8551677 (Open Web Text)

Max Activating Token Index: 374

Text #5

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.6790. Min Act: -0.1700

Data Index: 3366268 (Open Web Text)

Max Activating Token Index: 582

Text #6

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.6426. Min Act: -0.1700

Data Index: 5477251 (Open Web Text)

Max Activating Token Index: 887

Text #7

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.6515. Min Act: -0.1700

Data Index: 822562 (Open Web Text)

Max Activating Token Index: 387

Text #8

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.6094. Min Act: -0.1700

Data Index: 1575464 (Open Web Text)

Max Activating Token Index: 499

Text #9

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.6504. Min Act: -0.1700

Data Index: 793761 (Open Web Text)

Max Activating Token Index: 650

Text #10

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.6037. Min Act: -0.1700

Data Index: 3716868 (Open Web Text)

Max Activating Token Index: 503

Text #11

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.6243. Min Act: -0.1700

Data Index: 2342314 (Open Web Text)

Max Activating Token Index: 802

Text #12

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.5836. Min Act: -0.1700

Data Index: 3593684 (Open Web Text)

Max Activating Token Index: 593

Text #13

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.5844. Min Act: -0.1700

Data Index: 5165387 (Open Web Text)

Max Activating Token Index: 413

Text #14

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.5674. Min Act: -0.1700

Data Index: 3463685 (Open Web Text)

Max Activating Token Index: 381

Text #15

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.5770. Min Act: -0.1700

Data Index: 2172767 (Open Web Text)

Max Activating Token Index: 295

Text #16

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.5861. Min Act: -0.1700

Data Index: 3449956 (Open Web Text)

Max Activating Token Index: 716

Text #17

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.5906. Min Act: -0.1700

Data Index: 4995080 (Open Web Text)

Max Activating Token Index: 344

Text #18

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.6435. Min Act: -0.1700

Data Index: 3871727 (Open Web Text)

Max Activating Token Index: 501

Text #19

Max Range: 3.7896. Min Range: -3.7896

Max Act: 3.6188. Min Act: -0.1700

Data Index: 1561148 (Open Web Text)

Max Activating Token Index: 392