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

Dataset: Open Web Text

Neuron 1406 in Layer 1

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: 5.1647. Min Range: -5.1647

Max Act: 5.1647. Min Act: -0.1700

Data Index: 3832707 (Open Web Text)

Max Activating Token Index: 199

Text #1

Max Range: 5.1647. Min Range: -5.1647

Max Act: 5.0936. Min Act: -0.1700

Data Index: 6806791 (Open Web Text)

Max Activating Token Index: 113

Text #2

Max Range: 5.1647. Min Range: -5.1647

Max Act: 5.1168. Min Act: -0.1700

Data Index: 378055 (Open Web Text)

Max Activating Token Index: 750

Text #3

Max Range: 5.1647. Min Range: -5.1647

Max Act: 5.0907. Min Act: -0.1700

Data Index: 6328862 (Open Web Text)

Max Activating Token Index: 655

Text #4

Max Range: 5.1647. Min Range: -5.1647

Max Act: 5.0435. Min Act: -0.1700

Data Index: 2379007 (Open Web Text)

Max Activating Token Index: 300

Text #5

Max Range: 5.1647. Min Range: -5.1647

Max Act: 5.0337. Min Act: -0.1700

Data Index: 4973408 (Open Web Text)

Max Activating Token Index: 428

Text #6

Max Range: 5.1647. Min Range: -5.1647

Max Act: 5.0393. Min Act: -0.1700

Data Index: 3544586 (Open Web Text)

Max Activating Token Index: 431

Text #7

Max Range: 5.1647. Min Range: -5.1647

Max Act: 5.0000. Min Act: -0.1700

Data Index: 4226384 (Open Web Text)

Max Activating Token Index: 652

Text #8

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9878. Min Act: -0.1700

Data Index: 4317563 (Open Web Text)

Max Activating Token Index: 844

Text #9

Max Range: 5.1647. Min Range: -5.1647

Max Act: 5.0053. Min Act: -0.1700

Data Index: 3069355 (Open Web Text)

Max Activating Token Index: 373

Text #10

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9977. Min Act: -0.1700

Data Index: 3069352 (Open Web Text)

Max Activating Token Index: 590

Text #11

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9620. Min Act: -0.1700

Data Index: 7484956 (Open Web Text)

Max Activating Token Index: 401

Text #12

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9732. Min Act: -0.1700

Data Index: 166070 (Open Web Text)

Max Activating Token Index: 200

Text #13

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9829. Min Act: -0.1700

Data Index: 7065377 (Open Web Text)

Max Activating Token Index: 190

Text #14

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9579. Min Act: -0.1700

Data Index: 4020049 (Open Web Text)

Max Activating Token Index: 560

Text #15

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9775. Min Act: -0.1700

Data Index: 8224405 (Open Web Text)

Max Activating Token Index: 591

Text #16

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9717. Min Act: -0.1700

Data Index: 4861383 (Open Web Text)

Max Activating Token Index: 11

Text #17

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9768. Min Act: -0.1700

Data Index: 2643120 (Open Web Text)

Max Activating Token Index: 550

Text #18

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9926. Min Act: -0.1700

Data Index: 3832708 (Open Web Text)

Max Activating Token Index: 987

Text #19

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9592. Min Act: -0.1700

Data Index: 5099562 (Open Web Text)

Max Activating Token Index: 785