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

Dataset: Open Web Text

Neuron 1310 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: 4.6923. Min Range: -4.6923

Max Act: 4.6797. Min Act: -0.1700

Data Index: 4849533 (Open Web Text)

Max Activating Token Index: 461

Text #1

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.6882. Min Act: -0.1700

Data Index: 7167067 (Open Web Text)

Max Activating Token Index: 943

Text #2

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.6917. Min Act: -0.1700

Data Index: 6893906 (Open Web Text)

Max Activating Token Index: 9

Text #3

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.6923. Min Act: -0.1700

Data Index: 865747 (Open Web Text)

Max Activating Token Index: 502

Text #4

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.6418. Min Act: -0.1700

Data Index: 3926482 (Open Web Text)

Max Activating Token Index: 1014

Text #5

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.5830. Min Act: -0.1700

Data Index: 5571428 (Open Web Text)

Max Activating Token Index: 372

Text #6

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.5655. Min Act: -0.1700

Data Index: 7339429 (Open Web Text)

Max Activating Token Index: 27

Text #7

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.5701. Min Act: -0.1700

Data Index: 1974220 (Open Web Text)

Max Activating Token Index: 483

Text #8

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.5571. Min Act: -0.1700

Data Index: 2537262 (Open Web Text)

Max Activating Token Index: 63

Text #9

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.5808. Min Act: -0.1700

Data Index: 6428891 (Open Web Text)

Max Activating Token Index: 176

Text #10

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.5443. Min Act: -0.1700

Data Index: 4535762 (Open Web Text)

Max Activating Token Index: 275

Text #11

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.5559. Min Act: -0.1700

Data Index: 3919582 (Open Web Text)

Max Activating Token Index: 415

Text #12

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.5304. Min Act: -0.1700

Data Index: 6940928 (Open Web Text)

Max Activating Token Index: 852

Text #13

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.4936. Min Act: -0.1700

Data Index: 8394057 (Open Web Text)

Max Activating Token Index: 853

Text #14

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.4842. Min Act: -0.1700

Data Index: 8421695 (Open Web Text)

Max Activating Token Index: 511

Text #15

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.5114. Min Act: -0.1700

Data Index: 7462614 (Open Web Text)

Max Activating Token Index: 86

Text #16

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.4708. Min Act: -0.1700

Data Index: 6114318 (Open Web Text)

Max Activating Token Index: 832

Text #17

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.4885. Min Act: -0.1700

Data Index: 5596739 (Open Web Text)

Max Activating Token Index: 627

Text #18

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.4712. Min Act: -0.1700

Data Index: 4133923 (Open Web Text)

Max Activating Token Index: 775

Text #19

Max Range: 4.6923. Min Range: -4.6923

Max Act: 4.4666. Min Act: -0.1700

Data Index: 5048273 (Open Web Text)

Max Activating Token Index: 907